Tableau MCP

https://github.com/tableau/tableau-mcp
Admin
Tableau MCP is a suite of developer primitives, including tools, resources, and prompts, designed to...
Tokens:113,714
Snippets:895
Trust Score:8.4
License:Apache-2.0
Update:1 month ago
Show doc for...
Tokens:
Raw
### Prompt #3: Getting a View

Source: https://github.com/tableau/tableau-mcp/blob/main/README.md

Example prompt to get a specific view by name and project.

```text
Show me the "Economy" view in the "Finances" project.
```

--------------------------------

### Start local development server with npm run start

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/README.md

Starts a local development server and opens a browser window. Most changes are reflected live without restarting the server.

```bash
npm run start
```

--------------------------------

### Start server commands (npm run start:http, start:http:apm, start:http:docker)

Source: https://github.com/tableau/tableau-mcp/blob/main/CLAUDE.md

Commands to start the server. `npm run start:http` starts the HTTP server on the default port 3927. `npm run start:http:apm` enables APM telemetry tracing, and `npm run start:http:docker` runs the server via Docker.

```bash
npm run start:http            # Start HTTP server (default port 3927)
npm run start:http:apm        # Start with APM telemetry tracing enabled
npm run start:http:docker     # Run via Docker container
```

--------------------------------

### Install dependencies with npm install

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/README.md

Installs the project dependencies for the Docusaurus-based documentation site.

```bash
npm install
```

--------------------------------

### Example tool description structure

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/developers/contributing.md

Shows the recommended structure for a tool description, including what the tool does, when to use it, what it returns, usage examples, and disambiguation notes.

```markdown
Retrieves metadata for a specific published datasource including its fields,
types, and descriptions. Use this tool when a user asks about the schema,
structure, or available fields of a datasource or when data source metadata is critical to part of your overall task, e.g query a datasource.

**Example Usage:**
- "What fields are in the Sales datasource?" →
    First call list-datasources to get the LUID, then call this tool.
- "Show me the schema of datasource abc-123" →
    datasourceId: "abc-123"

**Note:** This tool returns field metadata only. To query actual data,
use the query-datasource tool instead.
```

--------------------------------

### Limit argument example

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/projects/list-projects.md

Example of the limit argument used to fetch a specific number of projects from the requested page.

```text
500
```

--------------------------------

### Conversational Analytics Interaction Example

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/pulse/generate-pulse-insight-brief.md

An example of an interactive Q&A session regarding sales metrics.

```text
User: "What are the key insights for Sales?"
AI: "Sales is up 5% with growth in West region..."

User: "What factors contributed to the increase?"
AI: "The increase was driven by Technology category growth..."
```

--------------------------------

### query argument example (VizQL query JSON)

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/data-qna/query-datasource.md

Example of the `query` argument for the query-datasource tool. It selects the top 5 customers by total revenue, using a TOP filter on Customer Name measured by SUM(Sales), and sorts results by Sales descending.

```json
{
  "fields": [
    {
      "fieldCaption": "Customer Name"
    },
    {
      "fieldCaption": "Sales",
      "function": "SUM",
      "fieldAlias": "Total Revenue",
      "sortDirection": "DESC",
      "sortPriority": 1
    }
  ],
  "filters": [
    {
      "field": {
        "fieldCaption": "Customer Name"
      },
      "filterType": "TOP",
      "howMany": 5,
      "direction": "TOP",
      "fieldToMeasure": {
        "fieldCaption": "Sales",
        "function": "SUM"
      }
    }
  ]
}
```

--------------------------------

### Example result JSON

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/data-qna/query-datasource.md

Example result of a query-datasource call. Shows the returned data array with customer names and total revenue values.

```json
{
  "data": [
    {
      "Customer Name": "Sean Miller",
      "Total Revenue": 25043.05
    },
    {
      "Customer Name": "Tamara Chand",
      "Total Revenue": 19052.217999999997
    },
    {
      "Customer Name": "Raymond Buch",
      "Total Revenue": 15117.338999999998
    },
    {
      "Customer Name": "Tom Ashbrook",
      "Total Revenue": 14595.62
    },
    {
      "Customer Name": "Adrian Barton",
      "Total Revenue": 14473.571
    }
  ]
}
```

--------------------------------

### Page number argument example

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/projects/list-projects.md

Example of the pageNumber argument used to fetch a specific page of results.

```text
2
```

--------------------------------

### List Datasources example result

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/data-qna/list-datasources.md

Example result of the List Datasources tool. Shows the shape of the response: a flat object with a `data` array and a `totalAvailable` count. The `data` array contains at most 1000 items per page, and `totalAvailable` is the total number of data sources available for pagination, unaffected by the `limit` argument.

```json
{
  "data": [
    {
      "id": "2d935df8-fe7e-4fd8-bb14-35eb4ba31d45",
      "name": "Superstore Datasource",
      "description": "*Overview*: Superstore Datasource contains data about your profit and sales\n\n*What is a Row of Data?* Each row of data corresponds to a unique order.",
      "project": {
        "name": "Samples",
        "id": "cbec32db-a4a2-4308-b5f0-4fc67322f359"
      }
    }
  ],
  "totalAvailable": 1
}
```

--------------------------------

### License reclamation filter examples for list-users tool

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/users/list-users.md

JavaScript filter examples to identify license reclamation candidates: unlicensed users inactive for 6+ months, all users inactive this year, and high-value Creator licenses with no recent activity.

```javascript
// Find unlicensed users who haven't logged in for 6+ months
filter: "siteRole:eq:Unlicensed,lastLogin:lt:2025-11-01T00:00:00Z"

// Find all users who haven't logged in this year
filter: "lastLogin:lt:2026-01-01T00:00:00Z"

// Find high-value licenses (Creator) with no recent activity
filter: "siteRole:eq:Creator,lastLogin:lt:2025-12-01T00:00:00Z"
```

--------------------------------

### Example result (S3 mode)

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/views/get-view-image.md

Shows the JSON response when MCP_S3_BUCKET is set, returning a resource_link with a presigned URL to the rendered image.

```json
{
  "type": "resource_link",
  "uri": "https://example-bucket.s3.amazonaws.com/...presigned...",
  "name": "view-image.png",
  "mimeType": "image/png",
  "description": "Rendered view image stored in S3. This is a short-lived presigned URL."
}
```

--------------------------------

### Example result JSON for get-flow

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/flows/get-flow.md

Example JSON response from the get-flow tool. Shows the structure of a flow object including id, name, description, webpageUrl, fileType, timestamps, project, owner, tags, outputSteps, connections, and flowRuns. The flowRuns array contains ad-hoc run details with status, start/end times, and progress.

```json
{
  "id": "d00700fe-28a0-4ece-a7af-5543ddf38a82",
  "name": "Sales Cleanup",
  "description": "Cleans up the daily sales feed",
  "webpageUrl": "https://10ax.online.tableau.com/#/site/mcp-test/flows/3",
  "fileType": "tflx",
  "createdAt": "2024-11-06T04:57:55Z",
  "updatedAt": "2024-11-06T21:31:00Z",
  "project": {
    "id": "6f8a2966-e173-11e8-ae74-ffd84c19d7f3",
    "name": "Default",
    "description": "The default project that was automatically created by Tableau."
  },
  "owner": {
    "id": "711e59cf-d1c0-446e-be48-3673ae067f7b",
    "name": "jane.doe@example.com",
    "fullName": "Jane Doe",
    "email": "jane.doe@example.com",
    "siteRole": "Creator"
  },
  "tags": { "tag": [{ "label": "sales" }] },
  "outputSteps": [{ "id": "5e4c9a74-d29a-4f62-baa5-97c443440dfc", "name": "CoffeeChainOutputCSV" }],
  "connections": [
    {
      "id": "5fd1c1db-572f-4ebd-94e7-a09e212bc147",
      "type": "sqlserver",
      "serverAddress": "mySQLServer",
      "userName": "analyst",
      "embedPassword": true
    }
  ],
  "flowRuns": [
    {
      "id": "a1a1a1a1-1111-1111-1111-111111111111",
      "flowId": "d00700fe-28a0-4ece-a7af-5543ddf38a82",
      "status": "Success",
      "startedAt": "2025-04-01T10:00:00Z",
      "completedAt": "2025-04-01T10:05:00Z",
      "progress": 100
    }
  ]
}
```

--------------------------------

### Example result for List Metrics

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/pulse/list-pulse-metrics-from-metric-ids.md

Example JSON output of the Batch list metrics API call, returned when the `metricIds` argument is provided. Shows the structure of the metric data including specification, comparison, and metrics metadata.

```json
[
  {
    "id": "fd6c4aa0-f6d3-469e-b75b-d597435ae199",
    "specification": {
      "filters": [],
      "measurement_period": {
        "granularity": "GRANULARITY_BY_MONTH",
        "range": "RANGE_CURRENT_PARTIAL"
      },
      "comparison": {
        "comparison": "TIME_COMPARISON_PREVIOUS_PERIOD"
      }
    },
    "definition_id": "9ad098f4-49cf-4e8a-bec0-0ca803091dd0",
    "is_default": true,
    "schema_version": "1.0.0",
    "metric_version": 2,
    "is_followed": true
  }
]
```

--------------------------------

### Example result for Get Workbook

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/workbooks/get-workbook.md

This JSON object represents the structure of the data returned when querying a workbook, including its ID, name, project association, and a list of contained views with their respective usage counts.

```json
{
  "id": "222ea993-9391-4910-a167-56b3d19b4e3b",
  "name": "Superstore",
  "webpageUrl": "https://10ax.online.tableau.com/#/site/mcp-test/workbooks/1412200",
  "contentUrl": "Superstore",
  "project": {
    "name": "Samples",
    "id": "cbec32db-a4a2-4308-b5f0-4fc67322f359"
  },
  "showTabs": true,
  "defaultViewId": "9460abfe-a6b2-49d1-b998-39e1ebcc55ce",
  "tags": {},
  "views": {
    "view": [
      {
        "id": "9460abfe-a6b2-49d1-b998-39e1ebcc55ce",
        "name": "Overview",
        "createdAt": "2025-09-02T23:25:58Z",
        "updatedAt": "2025-09-02T23:25:58Z",
        "tags": {},
        "totalViewCount": 165
      }
    ]
  }
}
```

--------------------------------

### List Flow Runs example result

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/flows/list-flow-runs.md

Example JSON response from the List Flow Runs tool. Shows a single successful flow run with its id, flowId, status, timestamps, progress, and backgroundJobId, plus the MCP resultInfo indicating returnedCount and truncated. Use this to understand the shape of the response when inspecting flow run history.

```json
{
  "flowRuns": [
    {
      "id": "a1a1a1a1-1111-1111-1111-111111111111",
      "flowId": "d00700fe-28a0-4ece-a7af-5543ddf38a82",
      "status": "Success",
      "startedAt": "2025-04-01T10:00:00Z",
          "completedAt": "2025-04-01T10:05:00Z",
      "progress": 100,
      "backgroundJobId": "b2b2b2b2-2222-2222-2222-222222222222"
    }
  ],
  "mcp": {
    "resultInfo": {
      "returnedCount": 1,
      "truncated": false
    }
  }
}
```

--------------------------------

### Example result

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/projects/list-projects.md

The structure of the JSON response returned by the tool, containing the project data and the total count of available projects.

```json
{
  "data": [
    {
      "id": "af59ee84-a375-4cb4-84b9-eaa7864f59fb",
      "name": "default",
      "description": "The default project that was automatically created by Tableau.",
      "contentPermissions": "ManagedByOwner",
      "createdAt": "2026-05-13T14:58:28Z",
      "updatedAt": "2026-05-13T14:58:28Z",
      "owner": {
        "id": "b4ffd9cf-6d7f-4a2f-a7a0-3bee3691ad36"
      }
    },
    {
      "id": "986ed80f-0a39-4b8a-b5af-c8b3f1280ae7",
      "name": "Nested project 1",
      "description": "",
      "parentProjectId": "7de99ef3-0337-4959-8ffe-8d54fbb1f9aa",
      "contentPermissions": "ManagedByOwner",
      "createdAt": "2026-05-13T15:23:00Z",
      "updatedAt": "2026-05-13T15:23:00Z",
      "owner": {
        "id": "86d935d7-d99c-46a1-8188-00faeee15465"
      }
    }
  ],
  "totalAvailable": 2
}
```

--------------------------------

### Example JSON result from list-users tool

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/users/list-users.md

Shows the structure of the response when users are found, including user fields and MCP result info with truncation details.

```json
{
  "users": [
    {
      "id": "user-abc123",
      "name": "jsmith",
      "siteRole": "Creator",
      "email": "john.smith@example.com",
      "fullName": "John Smith",
      "lastLogin": "2026-05-20T10:30:00Z"
    },
    {
      "id": "user-def456",
      "name": "asmith",
      "siteRole": "Viewer",
      "email": "alice.smith@example.com",
      "fullName": "Alice Smith",
      "lastLogin": "2026-05-15T08:00:00Z"
    },
    {
      "id": "user-ghi789",
      "name": "bjones",
      "siteRole": "Unlicensed",
      "email": "bob.jones@example.com",
      "fullName": "Bob Jones",
      "lastLogin": "2024-12-01T12:00:00Z"
    }
  ],
  "mcp": {
    "resultInfo": {
      "returnedCount": 3,
      "truncated": true,
      "truncationReason": "requested-limit"
    }
  }
}
```

--------------------------------

### Filter expression examples

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/projects/list-projects.md

Examples of filter expressions used to query projects based on specific criteria.

```text
name:eq:Default
```

```text
topLevelProject:eq:true
```

```text
parentProjectId:eq:abc-123
```

```text
updatedAt:gt:2023-01-01T00:00:00Z
```

--------------------------------

### List Views example result

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/views/list-views.md

Example result of the List Views tool. The response is a flat object with a `data` array containing view objects and a `totalAvailable` number for pagination. The `data` array holds at most 1000 views per page, and `totalAvailable` is unaffected by the `limit` argument.

```json
{
  "data": [
    {
      "id": "9460abfe-a6b2-49d1-b998-39e1ebcc55ce",
      "name": "Overview",
      "createdAt": "2025-09-02T23:25:58Z",
      "updatedAt": "2025-09-02T23:25:58Z",
          "workbook": {
        "id": "222ea993-9391-4910-a167-56b3d19b4e3b"
      },
      "owner": {
        "id": "d2a1e1df-af8e-4f43-a4cc-34858b7f8b69"
      },
      "project": {
        "id": "cbec32db-a4a2-4308-b5f0-4fc67322f359"
      },
      "tags": {},
      "totalViewCount": 0
    }
  ],
  "totalAvailable": 1
}
```

--------------------------------

### List Flow Runs response shape and example result

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/flows/list-flow-runs.md

The first block shows the always-present response shape with flowRuns and mcp.resultInfo. The second block is the example result with a failed run and failureInsight, including a deep link to the run history.

```json
{
  "flowRuns": [
    /* one record per run, see "Example result" below */
  ],
  "mcp": {
    "resultInfo": {
      "returnedCount": 12,
      "truncated": false
    }
  }
}
```

```json
{
  "flowRuns": [
    {
      "id": "c3c3c3c3-3333-3333-3333-333333333333",
      "flowId": "d00700fe-28a0-4ece-a7af-5543ddf38a82",
      "status": "Failed",
      "startedAt": "2025-04-02T10:00:00Z",
      "completedAt": "2025-04-02T10:01:12Z",
      "progress": 100,
      "backgroundJobId": "b4b4b4b4-4444-4444-4444-444444444444"
    }
  ],
  "mcp": {
    "resultInfo": {
      "returnedCount": 1,
      "truncated": false
    },
    "failureInsight": {
      "failedRunCount": 1,
      "failedFlowCount": 1,
      "example": {
        "flowId": "d00700fe-28a0-4ece-a7af-5543ddf38a82",
        "runHistoryUrl": "https://10ax.online.tableau.com/#/site/mysite/flows/12345/runHistory"
      }
    }
  }
}
```

--------------------------------

### Request Workbook Upload example result

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/workbooks/request-workbook-upload.md

Example result returned by the Request Workbook Upload tool. Contains a presigned S3 PUT URL, an opaque workbookUploadId, an expiration timestamp, a maximum upload size, and required headers for the upload.

```json
{
  "workbookUploadId": "123e4567-e89b-42d3-a456-426614174000",
  "uploadUrl": "https://s3.example.com/signed-put",
  "expiresAt": "2026-08-12T18:05:00.000Z",
  "maxSizeBytes": 5000000000,
  "requiredHeaders": {
    "Content-Type": "application/octet-stream"
  }
}
```

--------------------------------

### ALLOWED_REQUEST_OVERRIDES examples

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/configuration/mcp-config/request-overrides.md

Three examples showing how to set ALLOWED_REQUEST_OVERRIDES to allow specific variables, all variables with restrictions, or all variables restricted by default. The first example allows only INCLUDE_DATASOURCE_IDS (restricted) and INCLUDE_WORKBOOK_IDS (unrestricted). The second allows all overrides unrestricted except MAX_RESULT_LIMIT and MAX_RESULT_LIMITS which are restricted. The third allows all overrides restricted.

```plaintext
1. ALLOWED_REQUEST_OVERRIDES=INCLUDE_DATASOURCE_IDS,INCLUDE_WORKBOOK_IDS:unrestricted

2. ALLOWED_REQUEST_OVERRIDES=*:unrestricted,MAX_RESULT_LIMIT:restricted,MAX_RESULT_LIMITS:restricted

3. ALLOWED_REQUEST_OVERRIDES=*
```

--------------------------------

### Example custom views list result in JSON

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/views/list-custom-views.md

Shows the JSON structure returned when listing custom views, including custom view metadata, view, workbook, and owner details.

```json
[
  {
    "id": "1db3a121-51ac-4435-b533-3053e698dfc8",
    "name": "My Custom View",
    "createdAt": "2026-03-26T17:34:21Z",
    "updatedAt": "2026-03-31T22:06:29Z",
    "lastAccessedAt": "2026-03-31T22:06:29Z",
    "shared": false,
    "view": {
      "id": "9460abfe-a6b2-49d1-b998-39e1ebcc55ce",
      "name": "Overview"
    },
    "workbook": {
      "id": "222ea993-9391-4910-a167-56b3d19b4e3b",
      "name": "Superstore"
    },
    "owner": {
      "id": "bbdee366-4a50-4c2c-a5c8-746da5b64483",
      "name": "andrew.young@tableau.com"
    }
  }
]
```

--------------------------------

### Content exploration example result with upstreamDatasources

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/content-exploration/search-content.md

Example response from content exploration showing workbook, view, and datasource entries. Workbook and view entries may include an upstreamDatasources array when lineage enrichment succeeds. Datasource entries include connection type, certification, extract, and data quality warning fields.

```json
[
  {
    "modifiedTime": "2025-09-19T18:52:18.475Z",
    "type": "workbook",
    "ownerId": 325277,
    "title": "Income Trends with Age",
    "ownerName": "Lucia Orange",
    "containerName": "Research",
    "luid": "d9870a9b-4934-4ebc-a9ee-5fc723c79590",
    "totalViewCount": 3061,
    "favoritesTotal": 1,
    "viewCountLastMonth": 105,
    "hasExtracts": true,
    "extractCreationPending": false,
    "upstreamDatasources": [
      {
        "luid": "2d935df8-fe7e-4fd8-bb14-35eb4ba31d45",
        "name": "Superstore Datasource"
      }
    ]
  },
  {
    "modifiedTime": "2025-08-28T20:11:05.699Z",
    "sheetType": "dashboard",
    "workbookDescription": "This dashboard contains KPIs for e bike manufactures within our network.",
    "type": "view",
    "ownerId": 461938,
    "title": "Manufacturer Overview",
    "ownerName": "Maria Stone",
    "parentWorkbookName": "eBikes Analytics",
    "luid": "b4457c0b-5eeb-4cbc-b1ae-47ed1d90cee7",
    "locationName": "2025 Reports",
    "totalViewCount": 3991,
    "favoritesTotal": 7,
    "projectName": "2025 Reports",
    "viewCountLastMonth": 567,
    "upstreamDatasources": [
      {
        "luid": "a9af708b-0d44-48f8-23e2-4ee4b12446b2",
        "name": "eBikes Analytics Datasource"
      }
    ]
  },
  {
    "modifiedTime": "2025-09-24T20:10:35.437Z",
    "type": "datasource",
    "ownerId": 411957,
    "title": "Test Report Data",
    "ownerName": "Bruce Springtail",
    "containerName": "Data Sources",
    "luid": "a9af708b-0d44-48f8-23e2-4ee4b12446b2",
    "totalViewCount": 42260,
    "favoritesTotal": 3,
    "viewCountLastMonth": 1947,
    "isConnectable": true,
    "datasourceIsPublished": true,
    "connectionType": "snowflake",
    "isCertified": false,
    "hasExtracts": true,
    "extractRefreshedAt": "2025-09-24T20:10:35.385Z",
    "extractUpdatedAt": "2025-09-24T20:10:35.385Z",
    "connectedWorkbooksCount": 228,
    "extractCreationPending": false,
    "hasSevereDataQualityWarning": false,
    "hasActiveDataQualityWarning": false
  }
]
```

--------------------------------

### Prompt #1: Querying Data

Source: https://github.com/tableau/tableau-mcp/blob/main/README.md

Example prompt to query data from the Superstore datasource. Asks for the top 5 states by sales in 2025.

```text
For the Superstore Datasource, what are the top 5 states with the most sales in 2025?
```

--------------------------------

### Example result of generate-pulse-metric-value-insight-bundle

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/pulse/generate-pulse-metric-value-insight-bundle.md

Example result of the generate-pulse-metric-value-insight-bundle tool, showing a JSON response with an insight group of type 'ban' containing a single insight of type 'popc'. The insight includes a markup string describing the metric change and a Vega-Lite visualization specification for a bar chart.

```json
{
  "bundle_response": {
    "result": {
      "insight_groups": [
        {
          "type": "ban",
          "insights": [
            {
              "result": {
                "type": "popc",
                "version": 1,
                "content": "",
                "markup": "<span data-type=\"metric\">Pulse Metric</span> was 135.0K units (Q2 2025), <span data-type=\"insight-type-keyword\">up 7.7%</span> (9.7K units) compared to the prior quarter (Q1 2025).",
                "viz": {
                  "$schema": "https://vega.github.io/schema/vega-lite/v5.json",
                  "encoding": {
                    "y": {
                      "field": "entityName",
                      "type": "nominal",
                      "sort": {
                        "field": "index",
                        "order": "ascending"
                      },
                      "axis": {
                        "title": null,
                        "offset": {
                          "expr": "contributorAxisOffset"
                        },
                        "domain": false,
                        "labelPadding": {
                          "expr": "includesNegativeValues ? contributorAxisLabelMaxWidth + 16 : contributorAxisLabelPadding"
                        },
                        "labelFont": {
                          "expr": "contributorAxisLabelFontFace"
                        },
                        "labelFontSize": {
                          "expr": "contributorAxisLabelFontSize"
                        },
                        "labelColor": {
                          "expr": "contributorAxisLabelColor"
                        }
                      }
                    },
                    "x": {
                      "axis": {
                        "labelOpacity": 0,
                        "grid": true,
                        "gridOpacity": {
                          "expr": "datum.value === 0 ? 1 : 0"
                        },
                        "title": null,
                        "gridWidth": {
                          "expr": "contributorAxisDomainWidth"
                        },
                        "gridColor": {
                          "expr": "contributorAxisDomainColor"
                        },
                        "gridCap": {
                          "expr": "contributorAxisDomainCap"
                        },
                        "domain": false,
                        "zindex": 1
                      },
                      "stack": null,
                      "field": "value",
                      "type": "quantitative",
                      "scale": {
                        "padding": {
                          "expr": "xScalePadding"
                        }
                      }
                    }
                  },
                  "layer": [
                    {
                      "name": "bar-chart",
                      "description": "Layer for the bar chart",
                      "params": [
                        {
                          "name": "highlight",
                          "select": {
                            "type": "point",
                            "on": "pointerover"
                          }
                        },
                        {
                          "name": "select",
                          "select": "point"
                        }
                      ],
                      "mark": {
                        "cornerRadiusTopLeft": {
                          "expr": "datum.value >= 0 ? 0 : barCornerRadius"
                        },
                        "cornerRadiusBottomLeft": {
                          "expr": "datum.value >= 0 ? 0 : barCornerRadius"
                        },
                        "binSpacing": 0,
                        "strokeWidth": 1,
                        "type": "bar",
                        "height": 24,
                        "cornerRadiusTopRight": {
                          "expr": "datum.value < 0 ? 0 : barCornerRadius"
                        },
                        "cornerRadiusBottomRight": {
                          "expr": "datum.value < 0 ? 0 : barCornerRadius"
                        }
                      },
                      "encoding": {
                        "color": {
                          "condition": [
                            {
                              "empty": false,
                              "value": {
                                "expr": "\n                  if(datum.average, contributorBarColorAverageActive,\n                    if(mode === 'favorable', contributorBarColorFavorableActive,\n                      if(mode === 'unfavorable', contributorBarColorUnfavorableActive,\n                        contributorBarColorUnspecifiedActive\n                      )\n                    )\n                  )"
                              }
                            }
                          ]
                        }
                      }
                    }
                  ]
                }
              }
            }
          ]
        }
      ]
    }
  }
}
```

--------------------------------

### List Workbooks example result (JSON)

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/workbooks/list-workbooks.md

Example result of the List Workbooks tool. Shows the shape of the response: a flat object with a `data` array of workbook objects and a `totalAvailable` count. The `data` array contains at most 1000 workbooks per page, and `totalAvailable` is the total number of workbooks available for pagination, unaffected by the `limit` argument.

```json
{
  "data": [
    {
      "id": "222ea993-9391-4910-a167-56b3d19e4b3",
      "name": "Superstore",
      "webpageUrl": "https://10ax.online.tableau.com/#/site/mcp-test/workbooks/1412200",
      "contentUrl": "Superstore",
          "project": {
        "name": "Samples",
        "id": "cbec32db-a4a2-4308-b5f0-4fc67322f359"
      },
      "showTabs": true,
      "defaultViewId": "9460abfe-a6b2-49d1-b998-39e1ebcc55ce",
      "tags": {}
    }
  ],
  "totalAvailable": 1
}
```

--------------------------------

### Run link checker with uvx linkchecker

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/README.md

Runs a link checker locally using the Python linkchecker project. Requires running build and serve first; it does not work with just npm run start.

```bash
cd docs
npm install
npm run build
npm run serve
uvx linkchecker --check-extern --no-warnings http://localhost:3000/tableau-mcp/ --ignore-url="tableau.github.io" --ignore-url="127.0.0.1"
```

--------------------------------

### Example result for listing flow tasks

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/flows/list-flow-tasks.md

Example response object for listing flow tasks. The flowTasks array contains one record per scheduled task, and mcp.resultInfo is always present with returnedCount, totalAvailable, and truncated fields. Use this shape to parse the endpoint's output.

```json
{
  "flowTasks": [
    {
      "id": "1bff10bb-57ae-43df-8774-a86d14aef432",
      "priority": 50,
      "consecutiveFailedCount": 2,
      "type": "RunFlowTask",
      "schedule": {
        "id": "36d6fab2-2a0a-432e-b464-9fe4229a9937",
        "name": "Every 2 Minutes",
        "state": "Active",
        "priority": 50,
        "createdAt": "2018-11-08T21:57:49Z",
        "updatedAt": "2018-11-09T17:30:08Z",
        "type": "Flow",
        "frequency": "Hourly",
        "nextRunAt": "2018-11-09T17:32:00Z"
      },
      "flow": {
        "id": "8a320dca-9151-41ea-8474-a0bb71961cc0",
        "name": "allUseCaseTFLX2"
      }
    }
  ],
  "mcp": { "resultInfo": { "returnedCount": 1, "truncated": false, "totalAvailable": 1 } }
}
```

--------------------------------

### Response to Prompt #2

Source: https://github.com/tableau/tableau-mcp/blob/main/README.md

Example response to the content exploration prompt. Provides workbook details including owner, project, views, last modified date, and workbook ID.

```text
The most viewed workbook within the last year is:

Global Connections
- Owner: John Doe
- Project: Marketing
- Views in last year: 523
- Last Modified: September 2, 2025
- Workbook ID: 111fb672-9401-4913-a167-17b3d89a3e4f
```

--------------------------------

### Run Tableau MCP with Node after building from source

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/getting-started/README.md

Configure your AI tool (MCP client) to use Tableau MCP after building from source. The project includes a template file config.stdio.json you can use as an example.

```json
{
  "mcpServers": {
    "tableau": {
      "command": "node",
      "args": ["full/path/to/build/index.js"],
      "env": {
        "SERVER": "https://my-tableau-server.com",
        "SITE_NAME": "my_site",
        "PAT_NAME": "my_pat",
        "PAT_VALUE": "pat_value"
      }
    }
  }
}
```

--------------------------------

### Response to Prompt #1

Source: https://github.com/tableau/tableau-mcp/blob/main/README.md

Example response to the querying data prompt. Lists the top 5 states with sales figures and a summary note.

```text
Based on the Superstore Datasource, here are the top 5 states with the most sales in 2025:
  1. California - $146,388.34
  2. New York - $93,922.99
  3. Washington - $65,539.90
  4. Texas - $43,521.76
  5. Pennsylvania - $42,688.31
California leads by a significant margin with over $146,000 in sales, followed by New York with nearly $94,000. These two states alone account for a substantial portion of the total sales across the top 5 states.
```

--------------------------------

### Executive Briefing Summary Request

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/pulse/generate-pulse-insight-brief.md

An example of a natural language request for a daily metric summary.

```text
"What should I know about my metrics today?"
→ AI-generated summary of key changes, trends, and recommendations
```

--------------------------------

### Example result (S3 mode)

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/views/get-custom-view-data.md

Shows the response when MCP_S3_BUCKET is set: returns a resource_link with a short-lived presigned URL to the CSV file in S3 instead of inlining the data.

```json
{
  "type": "resource_link",
  "uri": "https://example-bucket.s3.amazonaws.com/...presigned...",
  "name": "view-data.csv",
  "mimeType": "text/csv",
  "description": "View data (CSV) stored in S3. This is a short-lived presigned URL."
}
```

--------------------------------

### Run Tableau MCP server from local build

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/enterprise/tableau-server.md

Run the Tableau MCP server from a local build. The command starts the server from the build directory, and the output shows the server version and the streamable HTTP endpoint.

```shell
node build/index.js
```

```shell
tableau-mcp v1.17.12 streamable HTTP server available at http://localhost:3927/tableau-mcp
```

--------------------------------

### Prompt #2: Content Exploration

Source: https://github.com/tableau/tableau-mcp/blob/main/README.md

Example prompt to find the most viewed workbook in the last year.

```text
Find me the most viewed workbook within the last year.
```

--------------------------------

### Run Tableau MCP server with npx

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/enterprise/tableau-server.md

Start the Tableau MCP server via npx. Replace 'latest' with a specific version (e.g., 1.17.12) to prevent auto-upgrading. The output shows the server version and the streamable HTTP endpoint.

```shell
npx -y @tableau/mcp-server@latest
```

```shell
tableau-mcp v1.17.12 streamable HTTP server available at http://localhost:3927/tableau-mcp
```

--------------------------------

### createdAt and updatedAt filter examples

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/flows/list-flows.md

Illustrates valid ISO 8601 formats and rejected date formats for timestamp filtering.

```text
createdAt:gt:2025-01-01T00:00:00Z       # ✅ canonical
createdAt:gt:2025-01-01                 # ✅ auto-promoted to 2025-01-01T00:00:00Z
createdAt:gt:2025-01-01T00:00:00        # ❌ tool rejects (no timezone)
createdAt:gt:2025-01-01T00:00:00+00:00  # ❌ tool rejects (offset, not Z)
createdAt:gt:01/01/2025                 # ❌ tool rejects (locale-ambiguous)
```

--------------------------------

### ownerName filter examples

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/flows/list-flows.md

Demonstrates that ownerName matches only by display name, while emails and UUIDs return no results.

```text
ownerName:eq:Jane Doe                                   # ✅ matches by display name
ownerName:eq:jane.doe@example.com                       # ❌ silently returns 0 flows
ownerName:eq:711e59cf-d1c0-446e-be48-3673ae067f7b       # ❌ silently returns 0 flows
```

--------------------------------

### Example JSON result from List Jobs

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/jobs/list-jobs.md

Shows the response structure with two jobs: one successful and one failed. Each job includes id, status, jobType, priority, timestamps, progress, and title.

```json
[
  {
    "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
    "status": "Success",
    "jobType": "refresh_extracts",
    "priority": 50,
    "createdAt": "2026-05-20T10:00:00Z",
    "startedAt": "2026-05-20T10:00:05Z",
    "endedAt": "2026-05-20T10:05:00Z",
    "progress": 100,
    "title": "Refreshing Sales Data"
  },
  {
    "id": "b2c3d4e5-f6a7-8901-bcde-f12345678901",
    "status": "Failed",
    "jobType": "refresh_extracts",
    "priority": 50,
    "createdAt": "2026-05-21T08:00:00Z",
    "startedAt": "2026-05-21T08:00:02Z",
    "endedAt": "2026-05-21T08:01:30Z",
    "progress": 45,
    "title": "Refreshing Marketing Analytics"
  }
]
```

--------------------------------

### Example result: extract refresh task JSON response

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/tasks/list-extract-refresh-tasks.md

Shows the JSON response structure for extract refresh tasks, including fields like id, datasource or workbook id, and schedule details. The example includes two tasks: one for a datasource with a daily schedule and one for a workbook with a weekly schedule. Use this to understand the expected output when listing or refreshing extract tasks.

```json
[
  {
    "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
    "datasource": {
      "id": "2d935df8-fe7e-4fd8-bb14-35eb4ba31d45"
    },
    "schedule": {
      "id": "schedule-123",
      "name": "Daily Early Morning",
      "state": "Active",
      "frequency": "Daily",
      "nextRunAt": "2026-05-21T06:00:00Z",
      "frequencyDetails": {
        "intervals": {
          "interval": [
            {
              "hours": 6,
              "minutes": 0
            }
          ]
        }
      }
    }
  },
  {
    "id": "b2c3d4e5-f6a7-8901-bcde-f12345678901",
    "workbook": {
      "id": "3e046e08-f8a3-4f09-c26f-46fa5b8bef13"
    },
    "schedule": {
      "id": "schedule-456",
      "name": "Weekly Sunday",
      "state": "Active",
      "frequency": "Weekly",
      "nextRunAt": "2026-05-25T08:00:00Z",
      "frequencyDetails": {
        "intervals": {
          "interval": [
            {
              "weekDay": "Sunday",
              "hours": 8,
              "minutes": 0
            }
          ]
        }
      }
    }
  }
]
```

--------------------------------

### Cursor mcp.json configuration

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/enterprise/tableau-server.md

Example mcp.json configuration for Cursor that adds the Tableau MCP server URL.

```json
{
  "mcpServers": {
    "tableau": {
      "url": "http://127.0.0.1:3927/tableau-mcp"
    }
  }
}
```

--------------------------------

### Example JSON result for List Metric Definitions

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/pulse/list-all-pulse-metric-definitions.md

Shows the structure of a metric definition returned by the List Metric Definitions tool. Includes metadata, specification, extension options, insights options, comparisons, and other fields.

```json
[
  {
    "metadata": {
      "name": "Tableau MCP",
      "description": "",
      "id": "9ad098f4-49cf-4e8a-bec0-0ca803091dd0",
      "schema_version": "1.0.0",
      "metric_version": 1,
      "definition_version": 0
    },
    "specification": {
      "datasource": {
        "id": "2d935df8-fe7e-4fd8-bb14-35eb4ba31d45"
      },
      "basic_specification": {
        "measure": {
          "field": "Profit",
          "aggregation": "AGGREGATION_SUM"
        },
        "time_dimension": {
          "field": "Order Date"
        },
        "filters": []
      },
      "is_running_total": true
    },
    "extension_options": {
      "allowed_dimensions": ["City"],
      "allowed_granularities": [
        "GRANULARITY_BY_DAY",
        "GRANULARITY_BY_WEEK",
        "GRANULARITY_BY_MONTH",
        "GRANULARITY_BY_QUARTER",
        "GRANULARITY_BY_YEAR"
      ],
      "offset_from_today": 0
    },
    "metrics": [],
    "total_metrics": 1,
    "representation_options": {
      "type": "NUMBER_FORMAT_TYPE_NUMBER",
      "number_units": {
        "singular_noun": "",
        "plural_noun": ""
      },
      "sentiment_type": "SENTIMENT_TYPE_NONE",
      "row_level_id_field": {
        "identifier_col": "City"
      },
      "row_level_entity_names": {
        "entity_name_singular": "",
        "entity_name_plural": ""
      },
      "row_level_name_field": {
        "name_col": ""
      },
      "currency_code": "CURRENCY_CODE_UNSPECIFIED"
    },
    "insights_options": {
      "settings": [
        {
          "type": "INSIGHT_TYPE_RISKY_MONOPOLY",
          "disabled": false
        },
        {
          "type": "INSIGHT_TYPE_TOP_DRIVERS",
          "disabled": false
        },
        {
          "type": "INSIGHT_TYPE_CURRENT_TREND",
          "disabled": false
        },
        {
          "type": "INSIGHT_TYPE_BOTTOM_CONTRIBUTORS",
          "disabled": false
        },
        {
          "type": "INSIGHT_TYPE_TOP_DETRACTORS",
          "disabled": false
        },
        {
          "type": "INSIGHT_TYPE_NEW_TREND",
          "disabled": false
        },
        {
          "type": "INSIGHT_TYPE_UNUSUAL_CHANGE",
          "disabled": false
        },
        {
          "type": "INSIGHT_TYPE_RECORD_LEVEL_OUTLIERS",
          "disabled": false
        },
        {
          "type": "INSIGHT_TYPE_CORRELATED_METRIC",
          "disabled": false
        }
      ]
    },
    "comparisons": {
      "comparisons": [
        {
          "compare_config": {
            "comparison": "TIME_COMPARISON_PREVIOUS_PERIOD"
          },
          "index": 0
        },
        {
          "compare_config": {
            "comparison": "TIME_COMPARISON_YEAR_AGO_PERIOD"
          },
          "index": 1
        }
      ]
    },
    "datasource_goals": []
  }
]
```

--------------------------------

### Example result (default)

Source: https://github.com/tableau/tableau-mcp/blob/main/docs/docs/tools/views/get-custom-view-data.md

Shows the default response when MCP_S3_BUCKET is unset: the CSV is returned as a single JSON-encoded text string with newlines escaped as \n.

```text
"Country/Region,State/Province,Profit Ratio,Latitude (generated),Longitude (generated)\nCanada,Ontario,26.8%,50.94,-84.75\n"
```
Tokens:
Raw