You are here:
Tableau Next Model Context Protocol (MCP) Server Tool Reference
Tableau Next MCP (Model Context Protocol) Server provides a suite of tools that allow external AI agents to interact with your analytical ecosystem.
Required Editions
| View supported editions. |
After you complete the initial setup, you no longer need to manually select or configure these tools. Ask your preferred MCP-compliant AI client (such as ChatGPT, Claude, or Cursor) questions using natural language, and it automatically selects the right tools for the task.
For example, when you ask, "What are my best product sales in 2025?", the AI agent uses the Analytics Q&A tool analyze_data to query your governed data via Concierge. The integration returns accurate answers and visualizations directly within your chat interface.
For documentation purposes, the available tools are grouped by their functional role within an analytical workflow.
Analysis
External MCP-compliant AI agents use these tools to query data and explore visual assets.
| Tool Name | Description / Inputs | Returns | Use When |
|---|---|---|---|
analyze_data |
Execute a natural-language question via the Analytics Agent against a target semantic model. |
answer (string; natural-language result). No metadata or
SQL. |
You want the agent to answer a question. If a complex question fails, break it down to multiple, simpler questions to retrieve key information and perform deep thinking on the client side. Don’t use this tool for metadata discovery. |
list_dashboards |
Enumerate Tableau Next dashboards (metadata only) for discovery and selection | Items with id, name/label, owning workspace (id/name), lastModifiedDate (when available). | You need dashboard identifiers or to browse dashboards (for metadata). |
get_dashboard |
Retrieve a single dashboard. | Full dashboard metadata. | You need the full details of a specific dashboard. |
list_visualizations |
Enumerate visualizations/worksheets (metadata only) across Tableau Next. | Items with id, name/label, parent dashboard/workbook, owning workspace, timestamps. | You need to discover charts or worksheets by name or parent.Not for images or query results |
get_visualization |
Retrieve a single visualization. | Full visualization metadata. | You need the full details of a specific visualization. |
Semantic Model Structure Discovery
External MCP-compliant AI agents use these tools to understand Tableau Next’s schemas, relationships, and logical views. The agents use this data architecture to make sense of the tables and connections inside Tableau Next.
| Tool Name | Description / Inputs | Returns | Use When |
|---|---|---|---|
list_semantic_models |
Enumerate semantic models available to the caller. | count, items [ ] with id, apiName, label, optional description, dataspace, categories. | You need to pick which semantic model to target next. |
get_semantic_model |
Retrieve the profile of a single semantic model, including business preferences. | apiName, label, businessPreferences (string with # guidance lines), and other semantic model properties. | You need model-level rules/guidance before querying or exploring internals. |
list_semantic_model_data_objects |
List data objects/entities defined in a semantic model. | items[ ] with apiName, label, dataObjectName, filters[ ]. |
You need to enumerate the building blocks (tables/entities) of a semantic model. |
list_semantic_model_relationships |
List relationships between data objects in a semantic model. | items[ ] with apiName, label, leftSemanticDefinitionApiName, rightSemanticDefinitionApiName, joinType, criteria. | You need to enumerate the relationships between data objects in a semantic model. |
get_semantic_model_logical_view |
Retrieve the structure of a single logical view. | apiName, label, semanticDataObjects[ ] (objects in the view), semanticRelationships[ ] (joins), semanticUnions[ ] , filters[ ]. | You need to understand the join graph and exposed fields of a specific view. |
Business Logic and Definitions
External MCP-compliant AI agents use these tools to identify specific Tableau Next KPIs and calculation logic.
| Tool Name | Description / Inputs | Returns | Use When |
|---|---|---|---|
list_semantic_model_measures |
List measures for a specific data object in a semantic model (numeric fields used for aggregation). | Measure metadata per object (name/apiName, label, data type, role) where available. | You need aggregateable fields exposed by a specific object. |
list_semantic_model_dimensions |
List dimensions for a specific data object in a semantic model (categorical/date/text fields used for grouping/slicing). | Dimension metadata per object (name/apiName, label, data type, role) where available. | You need group-by fields exposed by a specific object. |
list_semantic_model_metrics |
List business metrics/KPIs defined in a semantic model. | metrics[ ] with apiName, label. | You need named KPIs rather than raw fields or formulas. |
get_semantic_model_metric |
Retrieve the full definition of a single metric/KPI. | apiName, label, measurementReference (e.g., calculatedFieldApiName), timeDimensionReference (table/field), additionalDimensions, timeGrains[ ], filters[ ], aggregationType, isCumulative. | You must understand exactly how a KPI is computed and sliced. |
list_semantic_model_calculated_dimensions |
List calculated dimensions (user-defined expressions that yield categorical/date/text) in a semantic model. | Calculated dimension entries with identifiers, labels, and (where available) expression/typing details. | You need derived grouping fields defined at the model level. |
list_semantic_model_calculated_measures |
List calculated measures (user-defined numeric expressions/aggregations) in a semantic model. | items[ ] with apiName, label, dataType, expression, displayCategory, level (e.g., Row, AggregateFunction), aggregationType. | You need numeric derived fields and their formulas (building blocks for KPIs/metrics). |
Workspace and General Asset Discovery
External MCP-compliant AI agents use these tools to navigate Tableau Next’s environment and search for relevant analytical assets.
| Tool Name | Description / Inputs | Returns | Use When |
|---|---|---|---|
list_workspaces |
Enumerate workspaces or fetch one by id when provided. | workspaces[ ] with id, name, label, description, createdBy/Date, lastModifiedBy/Date, permissions (view/edit/share/delete), url. | You need containers and access context for assets. |
list_workspace_assets |
List assets contained in a specific workspace. | workspaceAssets[ ] with assetId, assetType (AnalyticsDashboard | AnalyticsVisualization | SemanticModel), assetUsageType (Created | Referenced), createdBy (id/name), createdDate, url. | You need dashboards, visualizations, and semantic models scoped to a workspace. |
search_assets |
Search for assets using a keyword and optional type filter to quickly discover relevant items. | assets[ ] including id, name, type, createdBy, createdDate, lastModifiedBy, lastModifiedDate. | You need broad or initial discovery of assets. If you need to browse assets in a structured hierarchy, use list tools instead. |
