Skip to main content

index

title: MCP Tool Reference sidebar_label: Overview sidebar_position: 0 doc_type: reference​

MCP Tool Reference

Overview​

Complete catalog of tools exposed by the MCP server. Each tool can be called from any compatible MCP client (Claude Desktop, Claude Code, VS Code, etc.).

Catalog​

CategoryToolsDescription
Ontology65Query, create, and navigate your business model.
Workflows16List, run, and monitor your automated workflows.
Knowledge Base16Search your documents, ask questions, and leverage your knowledge base.
Agent12Invoke AI agents, review sessions, and analyze performance.
Governance12Manage approvals, classifications, lineage, and data quality.
Calendar10Create events, manage calendars, and check availability.
Dashboard7View statistics, trends, and KPIs for your workspace.
Spreadsheets7Read, write, and query your collaborative spreadsheets.
Live Data5View your connected data sources and their schemas.
Administration5Check system health and maintenance statistics.
Bundles4Browse and import pre-built configuration packs.

All tools​

ToolCategoryScopeDescription
ontology_action_historyOntologymcp.read[READ] View the execution history for a Kinetic action. USE WHEN: - Need to see past execution results (success/failure) - Want to debug why an action failed - Need to check when an action was last run RETURNS: List of executions with status, duration, and errors REQUIRES: actionId (UUID) RELATED: - ontology_get_action: Get action details and stats - ontology_execute_action: Run the action - ontology_list_actions: Find actions first EXAMPLE: "Show execution history for this action" -> this tool
ontology_add_mutationOntologymcp.writeAdd a mutation (change) to a what-if scenario. USE WHEN: Want to model a change in a scenario without affecting production. REQUIRES: scenarioId, entityType, entityId, operation RELATED: ontology_create_scenario, ontology_scenario_impact
ontology_analyze_schemaOntologymcp.read[ANALYSIS] Deep analysis of ontology schema: types, properties, patterns, metrics. USE WHEN: Need to understand the data model structure before queries or modifications RETURNS: Schema summary, node type analyses, graph patterns, recommendations REQUIRES: espaceId (optional - uses default if not provided) RELATED: ontology_describe (quick overview), ontology_traverse (explore specific areas) EXAMPLE: "Analyze the schema structure" or "What patterns exist?" → this tool
ontology_apply_saved_viewOntologymcp.readApply a saved view configuration and return matching instances. USE WHEN: Need to load instances using a pre-configured view (columns, filters, sorts). REQUIRES: viewId RELATED: ontology_list_saved_views, ontology_list_instances
ontology_apply_scenarioOntologymcp.writeApply a what-if scenario to production data (COW merge). DESTRUCTIVE. USE WHEN: Ready to commit scenario changes to production. Use dryRun=true to preview first. REQUIRES: scenarioId RELATED: ontology_scenario_impact, ontology_create_scenario
ontology_apply_solverOntologymcp.writeConvert a completed solver run into a standard scenario with proposed mutations. USE WHEN: Applying an optimization result as a reviewable scenario. REQUIRES: runId RELATED: ontology_execute_solver, ontology_apply_scenario
ontology_compare_scenariosOntologymcp.readCompare multiple what-if scenarios side by side with diff matrix. USE WHEN: Need to see differences between scenario variants. REQUIRES: scenarioIds (at least 2) RELATED: ontology_create_scenario, ontology_scenario_impact
ontology_computed_propertiesOntologymcp.read[COMPUTED] Manage computed (derived) properties on ObjectTypes. USE WHEN: - List computed properties on an ObjectType - Create a new formula-based or aggregation property - Evaluate a computed property for an entity instance OPERATIONS: - list: Get all computed properties for an ObjectType - create: Create a new computed property with formula - evaluate: Compute value for a specific entity instance REQUIRES: operation, objectTypeId; depends on operation: name/formula/dataType (create), propertyId/entityInstanceId (evaluate) RELATED: - ontology_get_property_schema: Get property definitions - ontology_get_node: Get ObjectType details EXAMPLE: "Add a computed property total_revenue on Customer" -> this tool
ontology_create_edgeOntologymcp.write[MUTATION] Create a new relationship (edge) between two nodes. USE WHEN: Need to connect two entities with a relationship RETURNS: Created edge with ID, source/target info REQUIRES: source (id or name), target (id or name), edgeType RELATED: ontology_update_edge (modify), ontology_delete_edge (remove), ontology_get_edge_properties (view) EXAMPLE: "Connect Customer to Order with owns relationship" → this tool
ontology_create_instanceOntologymcp.writeCreate a new object instance (record) for a given object type. USE WHEN: Need to create a new record in the digital twin. REQUIRES: objectTypeId, data RELATED: ontology_list_instances, ontology_update_instance
ontology_create_nodeOntologymcp.write[MUTATION] Create a new ObjectType or LinkType in the ontology. USE WHEN: Need to add a new entity type or relationship type to the model RETURNS: Created node with ID, confirmation message REQUIRES: type (ObjectType/LinkType), name; espaceId optional RELATED: ontology_update_node (modify), ontology_delete_node (remove) EXAMPLE: "Create a Customer entity" or "Add a new relationship type" → this tool
ontology_create_pipelineOntologymcp.writeCreate a data pipeline with typed blocks (sources, transforms, destinations). USE WHEN: Building a new ETL pipeline or data transformation flow. REQUIRES: name, blocks (array of typed blocks) RELATED: ontology_run_pipeline, ontology_preview_pipeline_block, ontology_get_pipeline
ontology_create_scenarioOntologymcp.writeCreate a new what-if scenario for copy-on-write modeling. USE WHEN: Want to test changes without affecting production data. REQUIRES: name RELATED: ontology_list_scenarios, ontology_add_mutation, ontology_scenario_impact
ontology_delete_edgeOntologymcp.write[MUTATION] Delete an existing edge (relationship) from the ontology. USE WHEN: Need to remove a relationship between nodes RETURNS: Deleted edge info, undo capability REQUIRES: edgeId NOTE: Deletion can be undone via workspace undo RELATED: ontology_create_edge (create), ontology_update_edge (modify), ontology_get_edge_properties (view) EXAMPLE: "Remove the owns relationship between Customer and Order" → this tool
ontology_delete_instanceOntologymcp.writeDelete an object instance by ID. USE WHEN: Need to remove a record from the digital twin. REQUIRES: instanceId RELATED: ontology_get_instance, ontology_list_instances
ontology_delete_nodeOntologymcp.write[MUTATION] Delete a node from the ontology (with optional edge cascade). USE WHEN: Need to remove an entity or relationship type from the model RETURNS: Confirmation with deleted node ID and edge count if cascade REQUIRES: nodeId OR nodeName; cascade=true to also delete connected edges RELATED: ontology_get_node (verify first), ontology_get_neighbors (check connections) EXAMPLE: "Delete the Customer entity" or "Remove unused LinkType" → this toolYou can specify either nodeId or nodeName.
ontology_describeOntologymcp.read[DISCOVERY] Get a high-level business overview of an ontology structure. USE WHEN: • Want summary before detailed queries • Need to understand what\
ontology_entity_data_schemaOntologymcp.read[SCHEMA] Get the column schema (names, types, nullability) for data linked to an entity. USE WHEN: - Need to understand the structure of entity data before querying - Want to know which columns are available for an entity - Need column types for filtering or writing data RETURNS: Column definitions with name, data type, and nullability REQUIRES: entityId (UUID of the ontology node) RELATED: - ontology_query_entity_data: Query the actual data - ontology_write_entity_data: Write data using this schema EXAMPLE: "What columns does the Customer entity have?" -> this tool
ontology_execute_actionOntologymcp.write[EXECUTE] Execute a Kinetic action attached to an entity. USE WHEN: - Need to trigger an automation action - Want to run a workflow or agent from an entity context - Triggering API calls or webhooks linked to entities RETURNS: Execution result with status and output REQUIRES: actionId (UUID) NOTE: WORKFLOW and AGENT types are queued; simple types execute inline RELATED: - ontology_list_actions: Find actions to execute - ontology_get_action: Check action config first - ontology_action_history: View execution history EXAMPLE: "Execute the notify-team action" -> this tool
ontology_execute_solverOntologymcp.writeRun an optimization solver to find optimal values for decision variables. USE WHEN: Need to optimize instance data under constraints. REQUIRES: solverId RELATED: ontology_apply_solver, ontology_compare_scenarios
ontology_explain_searchOntologymcp.read[ANALYSIS] Understand why nodes ranked as they did in ontology search. USE WHEN: - Debugging search quality or unexpected rankings - Refining queries based on score breakdown - Understanding which fields matched (name, description, properties) RETURNS: Per-field scores, match details, ranking factors, query analysis FEATURES: - Score breakdown by field (name, description, apiName, properties) - Query term analysis and normalization - Match highlighting with positions - Human-readable ranking factor explanations REQUIRES: query (min 2 chars); optional: nodeId, topK, espaceId RELATED: ontology_search (perform search), ontology_get_node (details) EXAMPLE: "Why did Customer rank above Lead?" → this tool
ontology_exportOntologymcp.read[EXPORT] Export the ontology structure as JSON. USE WHEN: - Need to backup the ontology structure - Want to version-control the schema - Export for migration or CI/CD RETURNS: Full ontology structure with ObjectTypes, LinkTypes, properties REQUIRES: none; optional: espaceId, includeInstances, format RELATED: - ontology_describe: Quick summary without full export - ontology_list_espaces: List available espaces first EXAMPLE: "Export the ontology structure" -> this tool
ontology_export_graphmlOntologymcp.read[EXPORT] Export ontology as GraphML format for use in Gephi or Cytoscape. USE WHEN: - Need to visualize the ontology in Gephi or Cytoscape - Want a standard graph exchange format - Need to analyze network topology externally RETURNS: GraphML XML string with node/edge counts REQUIRES: none (optional: espaceId, filters, options) RELATED: - ontology_export_rdf: Export as RDF/OWL - ontology_export: Export as JSON/YAML - ontology_generate_docs: Generate documentation EXAMPLE: "Export ontology for Gephi" -> this tool
ontology_export_rdfOntologymcp.read[EXPORT] Export ontology as RDF/OWL for semantic web interoperability. Supports Turtle, RDF-XML, N-Triples, and JSON-LD formats. USE WHEN: - Need semantic web compatible export - Want to import ontology into Protégé or other OWL editors - Need linked data format (JSON-LD) - Integration with triple stores (Fuseki, Blazegraph) RETURNS: RDF string in chosen format with triple count REQUIRES: none (optional: espaceId, format, options) RELATED: - ontology_export_graphml: Export as GraphML - ontology_export: Export as JSON/YAML - ontology_generate_docs: Generate documentation EXAMPLE: "Export ontology as Turtle RDF" -> this tool
ontology_find_pathOntologymcp.read[GRAPH] Find shortest path(s) between two nodes in the ontology graph. USE WHEN: Need to understand how two entities are connected RETURNS: Path(s) with nodes, edges, and distances ALGORITHMS: bfs (hop count), dijkstra (edge weights) REQUIRES: source (id or name), target (id or name) RELATED: ontology_traverse (explore from one node), ontology_impact_analysis (cascade effects) EXAMPLE: "How are Customer and Invoice connected?" or "Path from Lead to Deal" → this tool
ontology_generate_docsOntologymcp.read[EXPORT] Generate auto-documentation of the ontology in Markdown, HTML, or JSON. USE WHEN: - Need to generate documentation for the ontology - Want a human-readable summary with statistics - Creating reference documentation for the team - Need formatted output with tables of contents RETURNS: Formatted documentation string with section list REQUIRES: none (optional: espaceId, format, options) RELATED: - ontology_export_graphml: Export as GraphML - ontology_export_rdf: Export as RDF/OWL - ontology_describe: Quick summary EXAMPLE: "Generate ontology documentation in Markdown" -> this tool
ontology_generate_parametricOntologymcp.writeGenerate a what-if scenario from a parametric template with custom parameter values. USE WHEN: Creating scenarios from predefined templates with variable inputs. REQUIRES: templateId, parameterValues RELATED: ontology_compare_scenarios, ontology_create_scenario
ontology_get_actionOntologymcp.read[READ] Get detailed information about a specific Kinetic action, including execution stats. USE WHEN: - Need full details of an action (config, trigger, type) - Want to see execution statistics (success rate, avg duration) RETURNS: Action details + execution statistics REQUIRES: actionId (UUID) RELATED: - ontology_list_actions: Find actions first - ontology_execute_action: Execute this action - ontology_action_history: View execution history EXAMPLE: "Show me details of this action" -> this tool
ontology_get_edge_propertiesOntologymcp.read[SCHEMA] Get detailed edge properties including cardinality, cascade rules, and constraints. USE WHEN: Need to understand relationship constraints, cascade behavior, or cardinality RETURNS: Full edge property schema with cardinality (one-to-many), cascadeDelete, reverseName, constraints REQUIRES: At least one filter (edgeId, sourceNodeId, targetNodeId, or edgeType) RELATED: ontology_query_edges (basic listing), ontology_impact_analysis (cascade simulation) EXAMPLE: "What happens if I delete Account?" or "Is Customer->Order one-to-many?" → this tool
ontology_get_historyOntologymcp.read[READ] Time-travel query: get historical state of a node at a specific point in time. USE WHEN: Need to see what a node looked like in the past, debug changes, audit modifications RETURNS: Historical state, current state, event list REQUIRES: nodeId or nodeName OPTIONAL: asOf (ISO timestamp) or sequenceNumber to get state at that point RELATED: ontology_get_node (current state), ontology_query_nodes (search) EXAMPLE: "What did the Customer node look like yesterday?" → this tool with asOf
ontology_get_instanceOntologymcp.readGet full details of a specific object instance by ID. USE WHEN: Need details for a specific record. REQUIRES: instanceId RELATED: ontology_list_instances, ontology_update_instance
ontology_get_neighborsOntologymcp.read[GRAPH] Get all neighbors of a node in a single efficient call. USE WHEN: Need to see what entities connect to/from a specific node RETURNS: Inbound connections (pointing TO), outbound connections (pointing FROM) REQUIRES: nodeId OR nodeName (at least one required) RELATED: ontology_traverse (multi-level exploration), ontology_query_edges (filter edges) EXAMPLE: "What connects to Customer?" or "Show relationships for Order" → this tool
ontology_get_nodeOntologymcp.read[QUERY] Get complete details of a single node by ID or name. USE WHEN: Need full properties, metadata, and details of a specific entity RETURNS: Complete node with properties, position, status, groups, interfaces REQUIRES: nodeId OR nodeName (at least one required) RELATED: ontology_get_neighbors (see connections), ontology_query_nodes (search multiple) EXAMPLE: "Get details of Customer entity" or "Show node properties" → this tool
ontology_get_pipelineOntologymcp.readGet full details of a specific data pipeline. USE WHEN: Need pipeline configuration, mappings, schedule. REQUIRES: pipelineId RELATED: ontology_list_pipelines, ontology_run_pipeline
ontology_get_property_schemaOntologymcp.read[SCHEMA] Get complete property schema of a node with validation rules, tags, and metadata. USE WHEN: Need to understand property definitions, validation rules, or data constraints RETURNS: Full property schema with types, validation (format, min/max), tags (pii), metadata (indexable) REQUIRES: nodeId OR nodeName (at least one required) RELATED: ontology_get_node (basic info), ontology_analyze_schema (full espace analysis) EXAMPLE: "What validation rules does Lead have?" or "Which properties are PII?" → this tool
ontology_get_templateOntologymcp.readGet full details of a specific ontology template. USE WHEN: Want to preview a template before importing. REQUIRES: templateId RELATED: ontology_list_templates, ontology_import_template
ontology_impact_analysisOntologymcp.read[GRAPH] Analyze the impact of changing or deleting a node. USE WHEN: Need to understand dependencies before making changes RETURNS: Downstream dependents, upstream dependencies, cascade delete simulation REQUIRES: nodeId OR nodeName FEATURES: Cascade delete detection, impact severity scoring, depth traversal RELATED: ontology_find_path (specific paths), ontology_get_edge_properties (edge details) EXAMPLE: "What would break if I delete Customer?" or "Impact of changing API endpoint" → this tool
ontology_import_templateOntologymcp.writeImport a pre-built ontology template into the workspace. USE WHEN: Want to bootstrap an ontology from a template. REQUIRES: templateId RELATED: ontology_list_templates, ontology_get_template
ontology_list_actionsOntologymcp.read[DISCOVERY] List Kinetic actions (automations) attached to entities. USE WHEN: - Want to see what automations exist for an entity - Need to discover available actions in the workspace - Looking for specific action types (API_CALL, WEBHOOK, WORKFLOW, AGENT) RETURNS: List of actions with type, trigger, and status REQUIRES: none (optional: entityId, espaceId to filter) RELATED: - ontology_get_action: Get full details of an action - ontology_execute_action: Execute an action - ontology_action_history: View execution history EXAMPLE: "What automations does the Order entity have?" -> this tool
ontology_list_espacesOntologymcp.read[DISCOVERY] List available ontology espaces (canvases) in the workspace. USE WHEN: • Starting exploration with no espace ID known • Need to discover available ontologies • Finding the default espace for queries RETURNS: List of espaces with IDs, names, node counts, and the defaultEspaceId FEATURES: • Identifies default espace for auto-resolution • Optional node count inclusion • Filter by status (active/archived) REQUIRES: optional: includeNodeCounts, status, limit RELATED: • ontology_describe: Get overview of specific espace • ontology_query_nodes: Query nodes in an espace EXAMPLE: "What ontologies exist?" or "List my espaces" → this tool
ontology_list_instancesOntologymcp.readList instances (records) of a given object type. USE WHEN: Need to see all records for an entity type. REQUIRES: objectTypeId RELATED: ontology_get_instance, ontology_search_instances, ontology_create_instance
ontology_list_pipelinesOntologymcp.readList data pipelines in the workspace. USE WHEN: Need to see available pipelines, check pipeline status. RELATED: ontology_get_pipeline, ontology_run_pipeline, ontology_pipeline_status
ontology_list_saved_viewsOntologymcp.readList saved table views (column/filter/sort configurations) for an object type. USE WHEN: Need to see available saved views for a type, find default views. REQUIRES: objectTypeId RELATED: ontology_apply_saved_view, ontology_list_instances
ontology_list_scenariosOntologymcp.readList what-if scenarios with optional status filter. USE WHEN: Want to see available scenarios. RELATED: ontology_create_scenario, ontology_scenario_impact, ontology_apply_scenario
ontology_list_simulation_stepsOntologymcp.readRetrieve step-by-step results from a temporal simulation run. USE WHEN: Inspecting simulation timeline, KPI evolution, or rules fired. REQUIRES: runId RELATED: ontology_run_simulation, ontology_compare_scenarios
ontology_list_templatesOntologymcp.readList available pre-built ontology templates. USE WHEN: Want to see what ontology templates are available for import. RELATED: ontology_get_template, ontology_import_template
ontology_pipeline_statusOntologymcp.readGet the status of a pipeline run (latest or specific). USE WHEN: Need to check if a pipeline is running, completed, or failed. REQUIRES: pipelineId RELATED: ontology_run_pipeline, ontology_get_pipeline
ontology_preview_pipeline_blockOntologymcp.readPreview data at a specific block in a pipeline. Executes the DAG up to that block and returns sample rows. USE WHEN: Need to inspect data flow at a specific point in the pipeline. REQUIRES: pipelineId, blockId RELATED: ontology_run_pipeline, ontology_create_pipeline, ontology_get_pipeline
ontology_query_edgesOntologymcp.read[QUERY] Search and filter edges (relationships) between nodes in an ontology. USE WHEN: Looking for specific relationships, connections from/to a node RETURNS: List of edges with source/target nodes, edge types, properties REQUIRES: espaceId (optional - uses default if not provided) RELATED: ontology_get_neighbors (more efficient for single node), ontology_traverse (graph exploration) EXAMPLE: "Show all belongs_to relationships" or "What connects to Customer?" → this tool
ontology_query_entity_dataOntologymcp.read[DATA ACCESS] Query actual business data (records) linked to an ontology entity. USE WHEN: - Need to see real data synced from external sources (Airbyte) - Want to browse entity instances (rows in df_mapped tables) - Need to verify what data is linked to an ontology node RETURNS: Records, columns, stream info, pagination REQUIRES: entityId (UUID of the ontology node) RELATED: - ontology_entity_data_schema: Get column schema before querying - ontology_get_node: Get the ontology node details - ontology_write_entity_data: Create/update/delete records EXAMPLE: "Show me the data for the Customer entity" -> this tool
ontology_query_nodesOntologymcp.read[QUERY] Search and filter nodes (ObjectTypes, LinkTypes) in an ontology. USE WHEN: Looking for specific nodes by type, name, or status RETURNS: List of matching nodes with IDs, types, properties REQUIRES: espaceId (optional - uses default if not provided) RELATED: ontology_get_node (single node details), ontology_get_neighbors (connections) EXAMPLE: "Find all Customer entities" or "List ObjectTypes" → this tool
ontology_reference_graphOntologymcp.read[IMPACT] "Who uses this?" — Find all consumers of an ontology element and calculate change impact. USE WHEN: - Before modifying/deleting an ObjectType, property, or link - Need to understand what depends on an element - Impact analysis before schema changes RETURNS: List of consumers (workflows, agents, spreadsheets), reference stats, impact severity if changeType provided REQUIRES: sourceType, sourceId; optional: changeType (for impact analysis) RELATED: - ontology_impact_analysis: Cascade analysis (existing tool) - ontology_get_node: Get element details EXAMPLE: "What uses the Customer ObjectType?" -> this tool
ontology_run_pipelineOntologymcp.writeTrigger execution of a data pipeline. USE WHEN: Need to manually run a pipeline to sync data. REQUIRES: pipelineId RELATED: ontology_pipeline_status, ontology_get_pipeline
ontology_run_simulationOntologymcp.writeCreate and execute a temporal simulation on a scenario with rules. USE WHEN: Simulating how data evolves over time with conditions and actions. REQUIRES: scenarioId, timeConfig, rules RELATED: ontology_list_simulation_steps, ontology_compare_scenarios
ontology_scenario_impactOntologymcp.readAnalyze the impact of all mutations in a what-if scenario. USE WHEN: Want to understand what changes a scenario would make before applying. REQUIRES: scenarioId RELATED: ontology_apply_scenario, ontology_add_mutation
ontology_searchOntologymcp.read[SEARCH] Full-text search across ontology entities and relations. USE WHEN: • Need to find entities by name, description, or properties • Looking for nodes matching keywords RETURNS: Ranked list of matching nodes with scores and highlights FEATURES: • Prefix matching for autocomplete • Relevance-ranked results (PostgreSQL TSVECTOR) • Shows where matches occurred (name, description, properties) • Redis caching for fast repeat queries REQUIRES: query (min 2 chars); optional: espaceId, nodeType, includeProperties, limit RELATED: • ontology_get_node: Get full details of a found node • ontology_get_neighbors: See connections of a found node • ontology_query_nodes: Filter-based query (vs text search) EXAMPLE: "Find entities related to customer" → this tool with query "customer"
ontology_search_instancesOntologymcp.readSearch object instances by their JSONB data fields. USE WHEN: Need to find instances matching a text query across data fields. RETURNS: Instances with matched field info. RELATED: ontology_list_instances, ontology_get_instance
ontology_semantic_queryOntologymcp.read[NL QUERY] Ask questions about the ontology in natural language. USE WHEN: - User asks a question about data in the ontology - Need to traverse the graph without knowing exact types/filters - Natural language query like "which clients have expired contracts" RETURNS: Synthesized answer, matching entities, relationships, step-by-step explanation REQUIRES: query (2-1000 chars); optional: espaceId, maxResults, includeExplanation RELATED: - ontology_query_nodes: Structured query (needs type/filters) - ontology_search: Keyword search for entities - ontology_traverse: Manual graph traversal EXAMPLE: "Which clients are linked to expired contracts?" -> this tool
ontology_statsOntologymcp.read[STATS] Get ontology statistics: entity counts, type counts, property averages. USE WHEN: - Need a quick overview of ontology size and health - Want to see entity/type distribution across espaces - Monitoring ontology growth over time RETURNS: Workspace-level and optional espace-level statistics REQUIRES: none; optional: espaceId, includeEspaceBreakdown RELATED: - ontology_describe: Structural summary (types, edges) - ontology_list_espaces: List available espaces EXAMPLE: "How many entities are in the ontology?" -> this tool
ontology_traverseOntologymcp.read[GRAPH] Traverse the ontology graph from a starting node up to N levels deep. USE WHEN: Need to explore the broader context around an entity (multi-hop) RETURNS: Subgraph with all nodes, edges, paths, and traversal stats REQUIRES: startNodeId OR startNodeName, maxDepth (1-5, default 2) RELATED: ontology_get_neighbors (single-hop), ontology_analyze_schema (structure) EXAMPLE: "Show 2 levels around Customer" or "Map the Order context" → this tool
ontology_update_edgeOntologymcp.write[MUTATION] Update properties of an existing edge (relationship). USE WHEN: Need to modify edge type, cardinality, cascade rules, or other properties RETURNS: Updated edge with version info REQUIRES: edgeId, updates object RELATED: ontology_create_edge (create), ontology_delete_edge (remove), ontology_get_edge_properties (view) EXAMPLE: "Change Customer->Order cardinality to one-to-many" → this tool
ontology_update_instanceOntologymcp.writeUpdate an existing object instance with OCC support. USE WHEN: Need to modify instance data or display name. REQUIRES: instanceId, data or displayName RELATED: ontology_get_instance, ontology_delete_instance
ontology_update_nodeOntologymcp.write[MUTATION] Update an existing node\
ontology_value_typesOntologymcp.read[TYPES] Manage reusable value type definitions for property standardization. USE WHEN: - Need to see available value types (text, numeric, temporal, etc.) - Get details of a specific value type (constraints, formatting) - Understand what types are available for properties OPERATIONS: - list: List all value types (system + custom) - get: Get a specific value type by ID REQUIRES: operation; optional: valueTypeId (get), category/search/limit (list) RELATED: - ontology_get_property_schema: Get property definitions - ontology_get_node: Get ObjectType details EXAMPLE: "What value types are available?" -> this tool
ontology_write_entity_dataOntologymcp.write[WRITE] Create, update, or delete data rows linked to an ontology entity. USE WHEN: - Need to add a new record to an entity - Want to update an existing entity record - Need to delete a record from an entity RETURNS: Success status, row ID, and affected row count REQUIRES: entityId, operation (create|update|delete) - create: requires data object - update: requires rowId and data object - delete: requires rowId RELATED: - ontology_query_entity_data: Read data first - ontology_entity_data_schema: Check schema before writing EXAMPLE: "Add a new customer record" -> this tool with operation=create
workflow_cancelWorkflowsmcp.workflow.execute[CONTROL] Cancel a running or queued workflow execution. USE WHEN: • Need to stop a workflow taking too long • Aborting due to detected issues • Freeing resources from stuck execution RETURNS: Success status, previous status, cancellation confirmation FEATURES: • Cancels pending, queued, or running executions • BullMQ job cleanup for queued executions • Optional cancellation reason stored REQUIRES: runId (from workflow_execute); optional: reason RELATED: • workflow_status: Check status before cancelling • workflow_execute: Restart if needed EXAMPLE: "Stop the running workflow" or "Cancel execution X" → this tool
workflow_createWorkflowsmcp.write[WRITE] Create a new workflow definition. USE WHEN: • Need to programmatically create a new workflow • Building automation pipelines via MCP • Creating workflows from scratch or with pre-defined blocks RETURNS: Workflow ID, name, status, version NOTE: Creates a workflow via CQRS command. The flow definition can include blocks (nodes) and connections (edges). Use workflow_update to modify later. REQUIRES: name; optional: description, flowDefinition, canvasId RELATED: • workflow_update: Modify the workflow after creation • workflow_execute: Run the workflow • workflow_list: List existing workflows • workflow_validate: Validate workflow before execution EXAMPLE: "Create a workflow called Data Sync" → this tool
workflow_executeWorkflowsmcp.workflow.execute[EXECUTION] Trigger workflow execution with optional input variables. USE WHEN: • Ready to run a workflow after validation • Need to execute with custom input variables • Triggering manual or programmatic execution RETURNS: runId, taskId, streamUrl for tracking, initial status (queued) FEATURES: • Durable execution with automatic checkpointing • Crash recovery from last checkpoint • Async by default with SSE streaming support • Resolve by ID or name (case-insensitive) REQUIRES: workflowId OR workflowName; optional: inputs (key-value), async RELATED: • workflow_status: Track execution progress and result • workflow_cancel: Stop if needed • workflow_validate: Check before running EXAMPLE: "Run the daily report workflow" or "Execute with input X=5" → this tool
workflow_exportWorkflowsmcp.readExport a workflow as portable JSON for backup, transfer, or version control. USE WHEN: - Need to back up a workflow definition - Need to migrate a workflow between environments - Need to version-control a workflow in Git RETURNS: portable workflow JSON with checksums and metadata.
workflow_export_bulkWorkflowsmcp.readExport multiple workflows at once as portable JSON. USE WHEN: - Need to back up multiple workflows - Need to migrate a set of workflows between environments RETURNS: array of portable workflow definitions with count.
workflow_getWorkflowsmcp.read[QUERY] Get detailed workflow definition: blocks, connections, configuration. USE WHEN: • Need to understand workflow structure before execution • Debugging workflow behavior or connections • Reviewing block configurations RETURNS: Complete definition with blocks (type, position, config), connections, metadata FEATURES: • Resolve by ID or name (case-insensitive) • Optional includeDefinition flag to skip block details • Block type breakdown in summary REQUIRES: workflowId OR workflowName (at least one); optional: includeDefinition RELATED: • workflow_validate: Validate before execution • workflow_execute: Run the workflow • workflow_list: Find workflow by name first EXAMPLE: "Show the compliance workflow definition" → this tool
workflow_get_block_outputWorkflowsmcp.read[DEBUG] Get output and execution details of a specific workflow block. USE WHEN: • Debugging why a block failed or produced unexpected output • Inspecting AI block token usage • Understanding block execution timing RETURNS: Block input/output, errors, duration, token usage, execution logs FEATURES: • Token tracking for AI blocks (input/output/total) • Execution logs from workflow_events • Error details with stack traces • Variables produced by the block • Checkpoint and execution_trace fallback REQUIRES: runId, blockId; optional: includeInput, includeLogs RELATED: • workflow_get_variables: Get variable snapshot at this block • workflow_status: Get overall execution result EXAMPLE: "Why did block X fail?" or "Show output of the filter block" → this tool
workflow_get_variablesWorkflowsmcp.read[DEBUG] Get runtime variable values at any point in workflow execution. USE WHEN: • Debugging data flow between blocks • Understanding what values were available at specific point • Tracking variable changes through execution RETURNS: Variable names, values, types, sources; optional: changed variables from previous block FEATURES: • Checkpoint-based variable snapshots • Block-specific variable state (before that block) • Final state if no blockId specified • Internal variable filtering (__ prefix) • Variable diff from previous block REQUIRES: runId; optional: blockId (for snapshot), includeInternal RELATED: • workflow_get_block_output: Get block input/output details • workflow_status: Get overall execution result EXAMPLE: "What was the value of X?" or "Show variables before filter block" → this tool
workflow_importWorkflowsmcp.writeImport a workflow from portable JSON into the current workspace. USE WHEN: - Need to restore a backed-up workflow - Need to migrate a workflow from another environment - Need to import a workflow shared via Git RETURNS: import result with workflow ID and status. NOTE: Use dryRun=true to validate before actual import.
workflow_listWorkflowsmcp.read[DISCOVERY] List available workflows with status, triggers, and metadata. USE WHEN: • Need to discover available workflows in the workspace • Finding a workflow by name or status RETURNS: List of workflows with IDs, names, status, node counts, last run timestamps FEATURES: • Filter by status (draft, published, archived) • Search by name with ILIKE pattern matching • Pagination support (limit/offset) REQUIRES: optional: status, limit, offset, search RELATED: • workflow_get: Get full definition with blocks and connections • workflow_execute: Run a workflow • workflow_validate: Check before execution EXAMPLE: "What workflows exist?" or "Find the compliance workflow" → this tool
workflow_schedule_createWorkflowsmcp.write, mcp.workflow.execute[MUTATION] Create a scheduled trigger for a workflow. USE WHEN: • Need to run a workflow on a schedule • Setting up recurring automation (daily, hourly, weekly) • Creating time-based workflow triggers RETURNS: Created schedule ID, next run time, confirmation FEATURES: • Cron: Flexible expression (e.g., "0 9 * * MON-FRI") • Interval: Regular intervals (seconds, minutes, hours, days, weeks) • Specific: Fixed times on specific days • Timezone support (IANA format) • Concurrency control (maxConcurrent) • Timeout configuration REQUIRES: workflowId OR workflowName, name, scheduleType; then type-specific: cronExpression | intervalValue+intervalUnit | specificTimes RELATED: • workflow_schedule_list: View existing schedules • workflow_schedule_trigger: Test-run immediately • workflow_validate: Validate workflow before scheduling EXAMPLE: "Run the report workflow every day at 9am" → this tool with cron "0 9 * * *"
workflow_schedule_listWorkflowsmcp.read[DISCOVERY] List scheduled workflow triggers with their configuration and run statistics. USE WHEN: • Need to see scheduled workflows • Checking schedule status (active/paused) • Finding schedules for a specific workflow RETURNS: List of schedules with expressions, next run times, run statistics (total/success/failed) FEATURES: • Filter by workflow ID or status • Cron, interval, and specific time formats • Run statistics and last run status • Pagination support REQUIRES: optional: workflowId, status, limit, offset RELATED: • workflow_schedule_create: Create new schedule • workflow_schedule_trigger: Test-run a schedule now • workflow_list: Find workflow to schedule EXAMPLE: "What schedules exist?" or "When does the daily report run?" → this tool
workflow_schedule_triggerWorkflowsmcp.workflow.execute[EXECUTION] Manually trigger a scheduled workflow immediately. USE WHEN: • Need to run a scheduled workflow now for testing • Urgent execution outside normal schedule • Verifying schedule configuration works RETURNS: runId for tracking, schedule and workflow details FEATURES: • Immediate execution bypassing schedule timing • Does not affect regular schedule (next run unchanged) • Resolve by schedule ID or name • Full execution tracking via runId REQUIRES: scheduleId OR scheduleName RELATED: • workflow_status: Track execution with returned runId • workflow_schedule_list: Find schedule to trigger • workflow_execute: Direct workflow execution (not via schedule) EXAMPLE: "Run the daily report now" → this tool
workflow_statusWorkflowsmcp.read[MONITORING] Get current status and result of a workflow execution. USE WHEN: • Tracking a running workflow • Checking if execution completed • Retrieving final result or error RETURNS: Status (pending/running/completed/failed/cancelled), result, duration, errors, progress FEATURES: • Real-time progress percentage • Current block tracking • Execution duration calculation • Error details on failure REQUIRES: runId (from workflow_execute) RELATED: • workflow_get_variables: Debug variable values at any point • workflow_get_block_output: Get specific block output • workflow_cancel: Stop running execution EXAMPLE: "Check if workflow is done" or "Get execution result" → this tool
workflow_updateWorkflowsmcp.write[WRITE] Update an existing workflow definition. USE WHEN: • Need to modify workflow blocks, connections, or metadata • Changing workflow name, description, or status • Publishing or archiving a workflow RETURNS: Updated workflow ID, name, status, new version OCC: Provide expectedVersion to detect concurrent modifications. If another user modified the workflow, a version conflict error is returned. REQUIRES: workflowId; optional: name, description, flowDefinition, status, expectedVersion RELATED: • workflow_get: Get current workflow state before updating • workflow_create: Create a new workflow • workflow_validate: Validate updated workflow EXAMPLE: "Update workflow to add a new condition block" → this tool
workflow_validateWorkflowsmcp.read[VALIDATION] Pre-flight validation of workflow before execution. USE WHEN: • Before running a workflow to catch issues early • After modifying workflow structure • Debugging why workflow fails to start RETURNS: isValid, canExecute, issues list with severity/code/suggestions, structure summary FEATURES: • Block configuration validation (required fields, formats) • Circular dependency detection • External reference validation (agents, entities, subflows) • Variable usage analysis (undefined, unused) • Trigger and output block checks REQUIRES: workflowId OR workflowName; optional: checkReferences, checkCycles, checkVariables RELATED: • workflow_execute: Run if validation passes • workflow_get: Review structure if issues found EXAMPLE: "Validate before running" or "Check workflow for errors" → this tool
knowledge_analyticsKnowledge Basemcp.read[ANALYTICS] Get comprehensive analytics for the Knowledge Library. USE WHEN: - Need to assess knowledge base health and coverage - Want to find gaps in documentation - Monitor search usage and quality metrics RETURNS: Overview (counts, storage), usage (queries, top searches), coverage (by source/category), quality metrics REQUIRES: none (all optional); optional: espaceId, periodDays, staleDaysThreshold RELATED: - knowledge_search: Search documents - knowledge_list_sources: List sources EXAMPLE: "What is the coverage of our knowledge base?" -> this tool
knowledge_askKnowledge Basemcp.read[RAG Q&A] Ask a question and get an answer with citations from the Knowledge Library. USE WHEN: - User asks a question that should be answered from documents - Need synthesized answer with source citations - Want to query the knowledge base in natural language RETURNS: Answer text, confidence score, citations with page numbers, follow-up questions REQUIRES: query (2-2000 chars); optional: sourceIds, maxSources, answerLength RELATED: - knowledge_search: Raw document search without synthesis - knowledge_get_document: Get full document after finding via ask - knowledge_entity_docs: Find documents linked to a specific entity EXAMPLE: "What is our KYC onboarding process?" -> this tool
knowledge_bulk_reprocessKnowledge Basemcp.write[ADMIN] Trigger bulk reprocessing of knowledge documents. USE WHEN: - Documents failed initial processing and need retry - Embeddings need to be regenerated (model changed) - Need to reindex stale documents RETURNS: Job ID, status, affected document count NOTE: Default is dryRun=true (preview mode). Set dryRun=false to execute. REQUIRES: none required; optional: scopeType, sourceIds, documentIds, stages, dryRun, priority RELATED: - knowledge_analytics: Check which documents need reprocessing - knowledge_list_sources: List sources for scopeType=source EXAMPLE: "Reprocess all failed documents" -> this tool
knowledge_create_sourceKnowledge Basemcp.write[WRITE] Create a new document source in the knowledge library. USE WHEN: • Need to create a folder/source to organize documents • Setting up a new integration (GitHub, Confluence, etc.) • Creating an upload target for manual document ingestion RETURNS: Source ID, name, type, status SOURCE TYPES: • upload: Manual document uploads • github: GitHub repository • confluence: Confluence space • notion: Notion workspace • url_crawl: Web URL crawler • s3: S3 bucket REQUIRES: name, type; optional: description, config, syncFrequencyMinutes RELATED: • knowledge_upload_document: Upload documents to this source • knowledge_list_sources: List existing sources • knowledge_sync_source: Trigger source synchronization EXAMPLE: "Create a source for technical docs" → this tool
knowledge_delete_documentKnowledge Basemcp.write[WRITE] Delete a document from the knowledge library. USE WHEN: • Need to remove an obsolete or incorrect document • Cleaning up duplicate documents • Decommissioning outdated content RETURNS: Confirmation of deletion NOTE: This is a soft delete. The document is marked as deleted but can be recovered. Associated chunks, embeddings, and graph entities are cascaded. REQUIRES: documentId RELATED: • knowledge_list_documents: Find document IDs to delete • knowledge_get_document: Verify document before deleting EXAMPLE: "Delete document abc-123" → this tool
knowledge_entity_docsKnowledge Basemcp.read[BRIDGE] Find documents linked to an ontology entity. USE WHEN: - Need to find documentation about a specific entity - Bridge between ontology entities and knowledge documents - "What documents mention Customer?" type queries RETURNS: Entity info, linked documents with relevance, related entities REQUIRES: entityId (UUID); optional: entityType, includeLinkedEntities, limit RELATED: - knowledge_search: General document search - knowledge_ask: Ask questions about an entity - ontology_get_node: Get entity details EXAMPLE: "What documents are linked to entity X?" -> this tool
knowledge_explain_resultsKnowledge Basemcp.read[ANALYSIS] Understand why documents ranked as they did in search. USE WHEN: • Debugging search quality or unexpected rankings • Refining queries based on score breakdown • Understanding relevance signals for each result RETURNS: Per-stage scores (vector, lexical, graph, fusion), matched terms, ranking factors, query analysis FEATURES: • Score breakdown: vector (semantic), lexical (keywords), graph (entity links), fusion (RRF) • Query analysis: detected language, entity mentions, refinement suggestions • Per-chunk score details with match type classification • Human-readable ranking factor explanations REQUIRES: query (min 2 chars); optional: topK (default 3), espaceId, includeChunkDetails RELATED: • knowledge_search: Perform the actual search • knowledge_get_document: Get full document after analysis • knowledge_get_related: Explore related content EXAMPLE: "Why did doc X rank higher?" or "Explain search relevance" → this tool
knowledge_get_chunksKnowledge Basemcp.read[QUERY] Retrieve specific chunks from a document with hierarchical context. USE WHEN: • Need specific sections of a document after search • Want to expand context around cited chunks • Building citations for referenced content RETURNS: Chunk text with page numbers, section titles, parent context, entity mentions FEATURES: • Hierarchical parent chunk context for better understanding • Flexible retrieval: by chunk IDs or index range • Entity mention extraction from chunks • Section-level metadata (title, level) REQUIRES: documentId; optional: chunkIds (specific), startIndex/endIndex (range), includeParent, limit RELATED: • knowledge_get_document: Get full document metadata • knowledge_search: Find chunks first with relevance scores • knowledge_explain_results: Understand why chunks matched EXAMPLE: "Get chunks 5-10 from the compliance doc" or "Retrieve specific chunk by ID" → this tool
knowledge_get_documentKnowledge Basemcp.read[QUERY] Retrieve a document with full metadata and optional chunks. USE WHEN: • Need full document details after finding it in search • Want to examine document metadata, status, or processing info RETURNS: Document metadata (title, status, tags, pageCount, chunkCount), optionally with text chunks FEATURES: • Optional chunk inclusion with configurable limit • Full processing status visibility (indexed, failed, pending) • Token counts for context budget planning REQUIRES: documentId (from knowledge_search or knowledge_list_sources); optional: includeChunks, chunkLimit RELATED: • knowledge_get_chunks: Get specific chunks with hierarchical context • knowledge_get_related: Find similar documents • knowledge_search: Find documents first EXAMPLE: "Get the full compliance policy document" or "Show document details with chunks" → this tool
knowledge_get_relatedKnowledge Basemcp.read[DISCOVERY] Find documents related to a given document. USE WHEN: • Exploring connected knowledge from a starting document • Finding similar documents for cross-referencing • Discovering entity-linked content across the library RETURNS: Related docs by type (semantic, entity, metadata), shared entities, similarity scores FEATURES: • Multi-relationship discovery: semantic similarity, shared entities, metadata overlap • Graph-based entity link traversal • Configurable similarity threshold and relation types • Deduplication across relationship types REQUIRES: documentId; optional: relationTypes (semantic|entity|metadata), minSimilarity, limit, excludeIds RELATED: • knowledge_search: Find initial document to explore from • knowledge_get_document: Get full details of related docs • knowledge_explain_results: Understand why documents are related EXAMPLE: "What docs are similar to this?" or "Find related policies" → this tool
knowledge_list_documentsKnowledge Basemcp.read[DISCOVERY] List documents in the knowledge library with filtering and pagination. USE WHEN: • Need to see all documents in the workspace • Want to browse documents without a specific search query • Filtering documents by status, tags, category, or source • Checking processing status of documents RETURNS: Paginated document list with metadata (title, status, tags, counts) FEATURES: • Filter by status: pending, ready, error, etc. • Filter by tags, category, sourceId, espaceId • Simple text search in title/filename (use knowledge_search for semantic search) • Pagination with configurable page size • Sorting by creation date, title, or file size REQUIRES: All parameters optional; page/limit for pagination RELATED: • knowledge_search: For semantic/hybrid search with query • knowledge_get_document: Get full details of a specific document • knowledge_list_sources: List document sources EXAMPLE: "List all documents" or "Show documents with status error" or "What documents are in the library?" → this tool
knowledge_list_sourcesKnowledge Basemcp.read[DISCOVERY] List document sources in the knowledge library. USE WHEN: • Need to see where documents come from • Checking sync status of external sources • Auditing configured integrations (GitHub, Confluence, etc.) RETURNS: Sources list with type, status, sync timestamps, document counts FEATURES: • Multiple source types: upload, github, confluence, notion, drive, s3, url_crawl, airbyte • Sync status tracking (active, paused, error) • Last/next sync timestamps for monitoring REQUIRES: optional: type, status, espaceId, limit (default 50) RELATED: • knowledge_search: Find documents from specific sources • knowledge_get_document: Get document details including source EXAMPLE: "What sources are configured?" or "Show GitHub connections" → this tool
knowledge_searchKnowledge Basemcp.read[SEARCH] Perform hybrid search across knowledge library (vector + lexical + graph). USE WHEN: • Looking for information, documents, or answers in the knowledge base • Need semantic + keyword search combined RETURNS: Ranked results with document IDs, titles, relevant chunks, citations FEATURES: • Hybrid search: vector (semantic) + lexical (keyword) + graph (entity-linked) • RRF fusion for optimal ranking • Optional reranking with cross-encoder • Graph boost for entity-linked content REQUIRES: query (min 2 chars); optional: limit, tags, category, espaceId, graphBoost, useReranking RELATED: • knowledge_get_document: Get full doc after finding in search • knowledge_explain_results: Understand why results ranked as they did • knowledge_get_related: Find similar documents EXAMPLE: "Search for compliance policy" or "Find information about KYC" → this tool
knowledge_similarKnowledge Basemcp.read[SIMILARITY] Find documents similar to a given document. USE WHEN: - Want to find related/similar documents - Need to discover document clusters - Looking for potential duplicates RETURNS: List of similar documents with scores and overlapping topics REQUIRES: documentId (UUID); optional: limit, minScore RELATED: - knowledge_search: Search by text query - knowledge_get_related: Get related via graph EXAMPLE: "Find documents similar to this one" -> this tool
knowledge_sync_sourceKnowledge Basemcp.write[WRITE] Trigger synchronization of a knowledge source. USE WHEN: • Need to refresh documents from an external source • Re-ingesting after source configuration changes • Forcing a full re-sync to catch missed updates RETURNS: Ingestion run ID, status, run type RUN TYPES: • delta: Only process new/changed documents (faster, default) • full: Re-ingest all documents from source (slower, thorough) REQUIRES: sourceId; optional: runType (default: delta) RELATED: • knowledge_list_sources: Find source IDs • knowledge_create_source: Create a new source first EXAMPLE: "Sync the technical docs source" → this tool
knowledge_upload_documentKnowledge Basemcp.write[WRITE] Upload and ingest a document into the knowledge library. USE WHEN: • Need to add a new document to the knowledge base • Ingesting text content for RAG search • Uploading a file (PDF, Markdown, etc.) encoded as base64 RETURNS: Document ID, status (pending → processing pipeline), filename NOTE: Document goes through 6-stage processing pipeline (extract → chunk → embed → tree → entity link → graph). Use knowledge_get_document to check processing status. REQUIRES: title, content; optional: contentType, mimeType, description, tags, category, sourceId RELATED: • knowledge_get_document: Check document processing status • knowledge_create_source: Create a source to organize documents • knowledge_search: Search uploaded documents EXAMPLE: "Upload this text as a knowledge document" → this tool
agent_cancelAgentmcp.agent.execute[CONTROL] Cancel a running agent invocation. USE WHEN: • Agent is taking too long • Need to stop due to detected issues • User requested cancellation RETURNS: Success status, previous status, cancellation confirmation FEATURES: • Cancels pending or running tasks • Optional cancellation reason • Emits cancellation event for cleanup REQUIRES: taskId (from agent_invoke); optional: reason RELATED: • agent_status: Check status before cancelling • agent_invoke: Restart if needed EXAMPLE: "Stop the running agent" or "Cancel agent task X" → this tool
agent_create_from_templateAgentmcp.write[MUTATION] Create a new agent using one of 58+ pre-configured templates. USE WHEN: • Need to quickly create a specialized agent • Want pre-configured tools and system prompts for common use cases • Building agents for data analysis, compliance, document processing, etc. RETURNS: New agent ID, name, template used, tools enabled FEATURES: • 58+ templates: data-analyst, ontology-navigator, workflow-debugger, compliance-auditor, etc. • Discovery mode: Use templateId="list" to browse all templates • Customizable: Override system prompt, add/remove tools • Pre-configured LLM settings and safety configs REQUIRES: templateId (or "list"), name; optional: description, folderId, customizations RELATED: • agent_list: Browse created agents • agent_get: View agent configuration • agent_invoke: Execute the new agent EXAMPLE: "Create a data analyst agent" → this tool with templateId="data-analyst"
agent_getAgentmcp.read[QUERY] Get detailed agent definition: config, system prompt, tools, knowledge sources. USE WHEN: • Need to understand agent capabilities before invocation • Reviewing agent configuration (system prompt, model, tools) • Checking what knowledge sources an agent uses RETURNS: Complete definition with config, model, tools, knowledge sources, system prompt FEATURES: • Resolve by ID, API name, or display name • Shows tool configuration and knowledge sources • Includes versioning and template info REQUIRES: agentId OR apiName OR agentName (at least one) RELATED: • agent_invoke: Execute the agent • agent_get_history: View past conversations • agent_list: Find agent first EXAMPLE: "What can the KYC agent do?" or "Show agent configuration" → this tool
agent_get_historyAgentmcp.read[HISTORY] Get conversation history for an agent or specific session. USE WHEN: • Need context from previous conversations • Debugging past interactions • Reviewing agent usage patterns RETURNS: Sessions with messages, timestamps, status, original queries, execution details FEATURES: • Per-session message logs • Original query tracking • Duration and status per session • Correlation ID for request tracing • Pagination support REQUIRES: agentId OR agentApiName OR sessionId (at least one); optional: includeMessages, messageLimit, limit, offset RELATED: • agent_get_tool_calls: Detailed tool execution for a session • agent_invoke: Continue conversation with conversationId EXAMPLE: "What did we discuss before?" or "Show conversation history" → this tool
agent_get_performanceAgentmcp.read[ANALYTICS] Get aggregated performance metrics for an agent over time. USE WHEN: • Evaluating agent performance over time • Identifying bottlenecks or error patterns • Optimizing agent configuration RETURNS: Latency percentiles (p50/p95/p99), success rates, token usage, tool stats, health score FEATURES: • Configurable time ranges (1h, 24h, 7d, 30d) • Per-tool breakdown with success rates • LLM usage statistics with token counts • Error pattern analysis with fingerprinting • Health score with recommendations REQUIRES: agentId; optional: timeRange, includeToolBreakdown, includeLlmBreakdown, includeErrorAnalysis RELATED: • agent_get_tool_calls: Specific session tool calls • agent_get_history: Browse session details EXAMPLE: "How is my KYC agent performing?" or "Show agent metrics" → this tool
agent_get_tool_callsAgentmcp.read[DEBUG] Get all tool calls made by an agent during execution. USE WHEN: • Debugging agent behavior • Understanding how the agent produced its response • Analyzing tool execution patterns RETURNS: List of tool calls with inputs, outputs, status, durations, error details FEATURES: • Per-tool input/output preview • Duration tracking per call • Error details with type classification • Iteration tracking for loops • Success rate statistics REQUIRES: sessionId (conversationId from agent_invoke); optional: includeResults, includeErrors, limit RELATED: • agent_status: Get overall execution result • agent_get_history: Browse past sessions EXAMPLE: "What tools did the agent use?" or "Debug agent execution" → this tool
agent_invokeAgentmcp.agent.execute[EXECUTION] Invoke an agent with a message, returns task ID for tracking. USE WHEN: • Ready to ask the agent a question or perform a task • Starting or continuing a multi-turn conversation • Executing agent with custom context RETURNS: taskId for status tracking, conversationId for follow-up, streamUrl for SSE FEATURES: • Async execution with SSE streaming support • Multi-turn conversations via conversationId • Custom context injection • LangGraph state machine execution (Parse→Plan→Execute→Evaluate→Synthesize) REQUIRES: agentId OR apiName, message; optional: conversationId, context, streaming RELATED: • agent_status: Track execution progress and get result • agent_cancel: Stop running execution • agent_get_tool_calls: See what tools the agent used EXAMPLE: "Ask the KYC agent to check compliance" → this tool
agent_listAgentmcp.read[DISCOVERY] List available agents with status, type, and configuration. USE WHEN: • Need to discover available agents in the workspace • Finding an agent by name, type, or status RETURNS: List of agents with IDs, names, API names, status, types, versions FEATURES: • Filter by status (draft, published, archived) • Filter by agent type (conversational, task_executor, etc.) • Search by name or description • Pagination support REQUIRES: optional: status, agentType, folderId, search, limit, offset RELATED: • agent_get: Get full agent definition with config • agent_invoke: Execute an agent • agent_get_performance: View metrics EXAMPLE: "What agents exist?" or "Find the KYC agent" → this tool
agent_statusAgentmcp.read[MONITORING] Get current status and result of an agent invocation. USE WHEN: • Tracking a running agent execution • Checking if agent completed • Retrieving the final response RETURNS: Status (pending/running/completed/failed/cancelled), response text, tool calls, timing FEATURES: • Progress percentage for long-running tasks • Tool call results included • Error details on failure • Cancellation reason if stopped REQUIRES: taskId (from agent_invoke) RELATED: • agent_get_tool_calls: Detailed tool execution trace • agent_cancel: Stop running execution • agent_invoke: Start new execution EXAMPLE: "Is the agent done?" or "Get agent response" → this tool
agent_studio_get_definitionAgentmcp.read[READ] Get the full configuration of an agent from Agent Studio. USE WHEN: • Need to inspect agent model, temperature, and system prompt • Checking which tools an agent has access to • Reviewing agent configuration before modification RETURNS: Full agent definition including config (model, temperature, tools, systemPrompt) LOOKUP: Can find by agentId (UUID) or agentName (case-insensitive) REQUIRES: agentId OR agentName RELATED: • agent_studio_list_definitions: Find agents to inspect • agent_studio_update_definition: Modify agent config • agent_invoke: Run the agent EXAMPLE: "Show me the config of the Customer Support agent" → this tool
agent_studio_list_definitionsAgentmcp.read[DISCOVERY] List agent definitions from the Agent Studio. USE WHEN: • Need to discover available agents • Searching for agents by name or status • Auditing published vs draft agents RETURNS: Agent list with names, types, statuses, invocation counts FEATURES: • Filter by status (draft, published, archived) • Full-text search on name and description • Pagination support REQUIRES: none required; optional: status, search, agentType, folderId, limit, offset RELATED: • agent_studio_get_definition: Get full agent configuration • agent_studio_update_definition: Modify agent config • agent_invoke: Run an agent EXAMPLE: "What agents are available?" or "List published agents" → this tool
agent_studio_update_definitionAgentmcp.write[WRITE] Update an agent definition in the Agent Studio. USE WHEN: • Changing agent model, temperature, or provider • Updating the system prompt • Adding or removing tools from an agent • Publishing, archiving, or renaming an agent RETURNS: Updated agent ID, name, status, list of changed fields CONFIG: The config object supports partial updates. Only provided fields are changed. • config.modelConfig: { provider, model, temperature } • config.systemPrompt: New system prompt text • config.tools: Full replacement list of tool names REQUIRES: agentId; at least one of: name, description, config, status RELATED: • agent_studio_get_definition: Get current config before updating • agent_studio_list_definitions: Find agent IDs EXAMPLE: "Change agent model to GPT-4o and lower temperature to 0.3" → this tool
governance_apply_classificationGovernancegovernance.writeApply a data classification level to an entity. USE WHEN: Need to classify data as public, internal, confidential, or restricted. REQUIRES: entityType, entityId, level RELATED: governance_list_classifications
governance_approveGovernancegovernance.approveApprove a pending governance approval request. USE WHEN: A governance request needs to be approved. REQUIRES: approvalId RELATED: governance_reject, governance_get_approval
governance_catalog_searchGovernancegovernance.read[DISCOVERY] Search across the governance catalog (approvals, classifications, lineage). USE WHEN: Looking for governance records, searching the catalog. RETURNS: Search results across governance tables. RELATED: governance_list_approvals, governance_list_classifications, governance_query_lineage
governance_get_approvalGovernancegovernance.readGet full details of a specific governance approval request by ID. USE WHEN: Need details on a specific approval. REQUIRES: approvalId RELATED: governance_list_approvals, governance_approve, governance_reject
governance_list_approvalsGovernancegovernance.read[DISCOVERY] List governance approval requests with optional filtering. USE WHEN: Need to see pending, approved, or rejected governance requests. RETURNS: Paginated list of approval requests. RELATED: governance_get_approval, governance_request_approval
governance_list_classificationsGovernancegovernance.readList data classifications applied to entities. USE WHEN: Need to see what classifications exist, filter by level or entity. RETURNS: Paginated list of classifications. RELATED: governance_apply_classification
governance_quarantine_statusGovernancegovernance.readCheck quarantine status of entities. USE WHEN: Need to see quarantined entities, check if data is blocked. RETURNS: List of quarantined entities with reasons. RELATED: governance_run_health_check
governance_query_lineageGovernancegovernance.readQuery data lineage records to trace how data flows between entities. USE WHEN: Need to trace data provenance, understand data flow, or audit transformations. RETURNS: Lineage records showing source-to-target data flow. RELATED: governance_record_lineage, governance_catalog_search
governance_record_lineageGovernancegovernance.writeRecord a data lineage relationship between two entities. USE WHEN: Documenting how data flows from source to target. REQUIRES: sourceEntityType, sourceEntityId, targetEntityType, targetEntityId, operationType RELATED: governance_query_lineage
governance_rejectGovernancegovernance.approveReject a pending governance approval request with a reason. USE WHEN: A governance request must be denied. REQUIRES: approvalId, reason RELATED: governance_approve, governance_get_approval
governance_request_approvalGovernancegovernance.writeCreate a new governance approval request for an entity. USE WHEN: An entity needs approval before proceeding. REQUIRES: entityType, entityId RELATED: governance_list_approvals, governance_approve, governance_reject
governance_run_health_checkGovernancegovernance.adminRun data quality health checks (completeness, consistency, freshness). USE WHEN: Need to check data quality, run compliance checks. RETURNS: Health check results with scores. RELATED: governance_quarantine_status
calendar_check_overlapsCalendarmcp.read[READ] Check for scheduling conflicts within a proposed time range. USE WHEN: - Before creating or rescheduling an event to avoid double-booking - Need to find a free time slot across calendars - Validating availability for a proposed meeting time RETURNS: hasOverlaps flag, list of overlapping events with id/title/start/end, total count. REQUIRES: startAt and endAt (proposed time range) RELATED: - calendar_create_event: Create event after confirming no overlaps - calendar_update_event: Reschedule after confirming availability - calendar_list_events: Browse events in a time range EXAMPLE: "Is 2pm-3pm available?" or "Check for conflicts" → this tool
calendar_create_eventCalendarmcp.write[WRITE] Create a new event in a calendar. USE WHEN: - Need to schedule a new event, meeting, task, or reminder - Need to create recurring events (RRULE) - Need to link an event to an ontology entity (espaceId) RETURNS: Created event with id, calendarId, title, start/end, eventType, createdAt. REQUIRES: calendarId (from calendar_list), title, start/end times NOTE: All-day events use startOn/endOn (dates). Timed events use startAt/endAt (datetimes). RELATED: - calendar_list: Get calendarId first - calendar_check_overlaps: Verify no conflicts before creating - calendar_update_event: Modify the event after creation EXAMPLE: "Schedule a meeting tomorrow at 2pm" → this tool
calendar_delete_eventCalendarmcp.write[DESTRUCTIVE] Delete a calendar event permanently. USE WHEN: - Need to remove an event from the calendar - Need to cancel an appointment or meeting RETURNS: Confirmation with deleted flag and eventId. REQUIRES: eventId (UUID from calendar_list_events or calendar_get_event) WARNING: This action is destructive and cannot be undone. RELATED: - calendar_get_event: Verify event details before deleting - calendar_list_events: Find the event ID to delete EXAMPLE: "Delete the meeting" or "Cancel tomorrow\
calendar_entity_eventsCalendarmcp.read[READ] Get calendar events linked to a specific ontology entity. USE WHEN: - Need to find events related to a business entity (e.g. Client, Project, Deal) - Need to see the calendar context of an ontology node - Need to bridge ontology and calendar modules RETURNS: Array of events with id, title, calendarId, calendarName, startAt/startOn, status. REQUIRES: espaceId (UUID of the ontology entity) RELATED: - calendar_list_events: List events by time range instead - ontology_get_node: Get the linked ontology node details - calendar_get_event: Get full event details by ID EXAMPLE: "Show events linked to this client" → this tool
calendar_get_eventCalendarmcp.read[READ] Get full details of a specific calendar event by ID. USE WHEN: - Need complete event details (description, metadata, recurrence, location) - Need the version field for subsequent updates (OCC) - Need espaceId to see ontology entity link RETURNS: Full event with all fields including metadata, version, visibility, espaceId. REQUIRES: eventId (UUID from calendar_list_events) RELATED: - calendar_update_event: Modify this event (requires version) - calendar_list_attendees: See who is invited - calendar_delete_event: Remove this event EXAMPLE: "Show me the details of this meeting" → this tool
calendar_listCalendarmcp.read[DISCOVERY] List all calendars in the current workspace. USE WHEN: - Need to find a calendar by name or ID - Need calendar IDs for subsequent calendar tools (create/list events) - Getting started with calendar features RETURNS: Array of calendars with id, name, timezone, color, visibility, isPrimary, timestamps. RELATED: - calendar_list_events: List events in a calendar - calendar_create_event: Create an event in a calendar - calendar_sync_status: Check external sync connections EXAMPLE: "What calendars do I have?" or "Show my calendars" → this tool
calendar_list_attendeesCalendarmcp.read[READ] List all attendees of a calendar event with RSVP status. USE WHEN: - Need to see who is invited to an event - Need to check RSVP / response status for each attendee - Need to identify the organizer of an event RETURNS: Array of attendees with id, email, displayName, responseStatus, isOrganizer, isOptional. REQUIRES: eventId (UUID from calendar_list_events) RELATED: - calendar_get_event: Get full event details - calendar_list_events: Find the event ID EXAMPLE: "Who is attending the meeting?" or "Check RSVPs" → this tool
calendar_list_eventsCalendarmcp.read[DISCOVERY] List events within a time range, optionally filtered by calendar or type. USE WHEN: - Need to see upcoming events or browse agenda - Need to find events by date range, calendar, or event type - Need event IDs for subsequent operations (get, update, delete) RETURNS: Array of events with id, title, start/end datetimes, type, status, recurrence info. REQUIRES: start and end datetime range (ISO 8601) RELATED: - calendar_get_event: Get full event details by ID - calendar_list: Get calendar IDs for filtering - calendar_check_overlaps: Check for scheduling conflicts EXAMPLE: "Show events this week" or "List meetings for today" → this tool
calendar_sync_statusCalendarmcp.read[READ] Check the status of external calendar sync connections (Google, Outlook). USE WHEN: - Need to verify external sync is active and healthy - Need to troubleshoot sync issues (paused, error, revoked) - Need to see when last sync occurred RETURNS: Array of connections with id, provider, status (active/paused/error/revoked), lastSyncAt, calendarId. RELATED: - calendar_list: List local calendars EXAMPLE: "Is Google Calendar syncing?" or "Check sync status" → this tool
calendar_update_eventCalendarmcp.write[WRITE] Update an existing calendar event (partial update). USE WHEN: - Need to reschedule, rename, or modify an event - Need to change event type, status, visibility, or location - Need to link/unlink an ontology entity RETURNS: Updated event with id, title, new version, updatedAt. REQUIRES: eventId + version (from calendar_get_event for OCC) NOTE: Throws 409 on version conflict — re-fetch via calendar_get_event and retry. RELATED: - calendar_get_event: Get current version before updating - calendar_check_overlaps: Verify no conflicts when rescheduling EXAMPLE: "Reschedule the meeting to 3pm" → this tool
dashboard_agent_intelligenceDashboardmcp.readGet agent intelligence metrics: conversations, success rate, intent distribution, top tools. USE WHEN: - Need to understand agent usage patterns - Need agent success/failure rates - Need to see which tools agents use most RETURNS: agentHub (conversations, intents, topTools), agentStudio (agents, executions).
dashboard_alert_trendDashboardmcp.readGet hourly alert trend by severity (critical, warning, info). USE WHEN: - Need to monitor system alerts - Need to identify spikes in errors or warnings RETURNS: hourly breakdown of critical/warning/info alerts.
dashboard_api_trendsDashboardmcp.readGet API performance trends: success rate, average response time, total endpoints. USE WHEN: - Need to monitor API performance - Need to check success/error rates RETURNS: successRate, avgResponseTime (ms), totalEndpoints with trends.
dashboard_livedata_trendsDashboardmcp.readGet live data connection trends: active connections, data freshness, sync health. USE WHEN: - Need to monitor data ingestion health - Need to check sync freshness score RETURNS: activeConnections, dataFreshness (0-100), syncHealth (0-100) with trends.
dashboard_ontology_summaryDashboardmcp.readGet ontology-specific metrics: completeness, topology, categories, daily modifications. USE WHEN: - Need ontology health metrics (orphan nodes, completeness) - Need topology distribution (hub/connected/leaf/orphan) - Need category breakdown RETURNS: KPIs with trends, topology, top categories, daily chart data.
dashboard_overviewDashboardmcp.read[DISCOVERY] Get a complete dashboard overview with ontology, live data, and API trends. USE WHEN: - Need a high-level view of workspace health - Need to see all KPIs at once RETURNS: ontology completeness, live data health, API success rate, weekly modifications.
dashboard_top_endpointsDashboardmcp.readGet the slowest API endpoints by average response time (last 7 days). USE WHEN: - Need to identify slow endpoints - Need to optimize API performance RETURNS: path, method, avgResponseTime (ms), callCount.
spreadsheets_delete_rowsSpreadsheetsmcp.write[WRITE] Delete rows from a spreadsheet (manual tableurs only). USE WHEN: - Need to delete spreadsheet rows programmatically from an MCP client NOTES: - Source-linked spreadsheets are read-only. - Soft-deleted spreadsheets (trash) are blocked. RETURNS: rowsDeleted + rowIds deleted.
spreadsheets_getSpreadsheetsmcp.read[READ] Get spreadsheet metadata (columns, settings, rowCount) and tab list. USE WHEN: - Need column IDs / display names before reading rows - Need to understand sheet structure RETURNS: spreadsheet + tabs summary.
spreadsheets_get_schemaSpreadsheetsmcp.read[READ] Get spreadsheet schema (columns) and optional sample rows. USE WHEN: - Need column IDs/types before reading/writing rows - Need a quick preview of data shape RETURNS: columns[] (id/name/displayName/type) + optional sampleRows[].
spreadsheets_listSpreadsheetsmcp.read[DISCOVERY] List spreadsheets (tableurs) in the current workspace. USE WHEN: - Need to find a spreadsheet by name - Need IDs for subsequent spreadsheet tools RETURNS: id, name, rowCount, updatedAt, pinned/source-linked flags.
spreadsheets_query_nlSpreadsheetsmcp.read[READ] Query spreadsheet rows using natural language. USE WHEN: - Need to find rows matching business criteria without writing filters - Query across spreadsheets (or within a specific sheetId) RETURNS: matching rows + an explanation plan (interpreted query, filters, warnings).
spreadsheets_read_rowsSpreadsheetsmcp.read[READ] Read rows from a spreadsheet (optionally filtered by tab). USE WHEN: - Need actual row data for analysis - Need to page through a large spreadsheet RETURNS: rows with rowNumber and raw data (keys are column IDs).
spreadsheets_write_rowsSpreadsheetsmcp.write[WRITE] Insert/update/upsert rows in a spreadsheet (manual tableurs only). USE WHEN: - Need to programmatically write spreadsheet data from an MCP client NOTES: - Source-linked spreadsheets are read-only. - Soft-deleted spreadsheets (trash) are blocked. RETURNS: rowsAffected + rowIds.
livedata_list_sourcesLive Datamcp.read[DISCOVERY] List all connected live data sources with status and metadata. USE WHEN: • Need to discover available data sources • Checking status of connections • Finding a specific source by name or type RETURNS: List of sources (Airbyte, webhooks, HTTP, MQTT, IoT) with IDs, names, status, stream counts FEATURES: • Filter by category (airbyte, webhook, http, mqtt, iot, database, file) • Filter by status (active, inactive, error) • Search by name • Pagination support REQUIRES: optional: category, status, search, limit, offset RELATED: • livedata_source_status: Get health and activity details • livedata_source_schema: Get stream structure • livedata_query: Query actual data EXAMPLE: "What data sources exist?" or "List active connections" → this tool
livedata_queryLive Datamcp.read[QUERY] Query real-time data from connected sources with filters. USE WHEN: • Retrieving actual data records from live sources • Analyzing time-series data for an entity • Getting recent data from a specific stream RETURNS: Data records with timestamps, values, metadata, and time range summary FEATURES: • Time range filtering (ISO8601 startTime/endTime) • Filter by source, stream, or linked entity • TimescaleDB-backed for efficient time-series queries • Pagination support REQUIRES: optional: sourceId, streamId, entityId, startTime, endTime, limit, offset RELATED: • livedata_source_schema: Understand stream structure first • livedata_list_sources: Find source IDs EXAMPLE: "Get last 24h of sales data" or "Query records for Customer X" → this tool
livedata_source_schemaLive Datamcp.read[QUERY] Get schema and stream structure of a data source. USE WHEN: • Understanding what data a source provides • Before querying to know available streams • Checking which streams are linked to ontology nodes RETURNS: Streams list with names, namespaces, status, linked nodes, configuration FEATURES: • Stream status visibility (active, paused, error) • Linked ontology nodes per stream • Stream metadata and namespace • Source configuration details REQUIRES: sourceId (from livedata_list_sources) RELATED: • livedata_query: Query data from specific streams • livedata_source_status: Check source health first • livedata_list_sources: Find source first EXAMPLE: "What streams does Salesforce provide?" or "Show source schema" → this tool
livedata_source_statusLive Datamcp.read[MONITORING] Get detailed status and health information for a data source. USE WHEN: • Checking if a source is healthy • Debugging connection or sync issues • Monitoring source activity RETURNS: Health status, last sync time, error count, success rate, recent activity FEATURES: • Health score based on status and errors • Success rate calculation • Optional activity log with recent calls • Error message extraction REQUIRES: sourceId (from livedata_list_sources); optional: includeActivity RELATED: • livedata_source_schema: Get stream structure • livedata_query: Query data from healthy sources • livedata_list_sources: Find source first EXAMPLE: "Is my Salesforce source healthy?" or "Check source errors" → this tool
livedata_trigger_syncLive Datamcp.write[WRITE] Trigger a data synchronization for a LiveData connection. USE WHEN: • Need to refresh data from an external source (Stripe, Salesforce, etc.) • Want to manually trigger a sync outside the scheduled interval • Verifying that a data connection works after setup RETURNS: Connection ID, sync status, source name NOTE: The sync runs asynchronously via Airbyte. Use livedata_source_status to check progress. REQUIRES: connectionId (UUID of the Airbyte connection) RELATED: • livedata_list_sources: Find connection IDs • livedata_source_status: Check sync progress • livedata_query: Query synced data EXAMPLE: "Refresh the Stripe data" → this tool
admin_circuit_breaker_statusAdministrationmcp.readGet the status of all circuit breakers in the system. USE WHEN: - Need to check if any external services are failing - Need to see which circuit breakers are open - Debugging connectivity issues RETURNS: summary (healthy/unhealthy counts) and per-breaker status.
admin_dlq_statsAdministrationmcp.readGet statistics about the Dead Letter Queue (DLQ) for failed outbox events. USE WHEN: - Need to check if there are failed events in the DLQ - Need to see common error patterns - Need to monitor event processing health RETURNS: total events, breakdown by workspace/type, common errors.
admin_healthAdministrationmcp.read[DISCOVERY] Get system health overview with database and event store statistics. USE WHEN: - Need to check if the system is healthy - Need database connection pool statistics - Need event store metrics RETURNS: health status, database info, event store stats.
admin_orphan_cleanupAdministrationmcp.writeDetect and clean up orphan edges (edges referencing non-existent nodes). USE WHEN: - Need to check for orphan edges in the graph - Need to clean up orphan data after deletions RETURNS: orphan statistics or cleanup results. NOTE: dryRun defaults to true for safety — set to false to actually delete.
admin_projection_statsAdministrationmcp.readGet event store and projection statistics. USE WHEN: - Need to see how many events are in the store - Need to check event distribution by type - Need to monitor outbox health RETURNS: total events, events by type, stream count, date range, outbox stats.
bundle_getBundlesmcp.readGet detailed information about a specific bundle including all modules. USE WHEN: - Need to inspect a bundle\
bundle_importBundlesmcp.writeImport a use-case bundle into the current workspace. USE WHEN: - Want to set up a complete use-case (ontology + workflows + agents) - Need to bootstrap a workspace with pre-built templates RETURNS: import ID, status, created resources, and any errors. NOTE: Use bundle_preview first to check for conflicts.
bundle_listBundlesmcp.read[DISCOVERY] List available use-case bundles from the catalog. USE WHEN: - Need to see what pre-built bundles are available - Searching for a bundle by industry or complexity RETURNS: list of bundles with metadata (name, industry, complexity, resource counts).
bundle_previewBundlesmcp.readPreview what importing a bundle would create, update, or conflict with. USE WHEN: - Need to check for conflicts before importing - Want to see what resources will be created RETURNS: resources to create, conflicts with existing data, required connections.

Need help?​

Contact us: Support and contact.