Tableau MCP is a suite of developer primitives, including tools, resources, and prompts, designed to facilitate the creation of AI applications that integrate with Tableau. It simplifies the process for developers to leverage AI for interacting with Tableau data and content.

Is tableau-mcp open source?

Yes, licensed under Apache-2.0.

tableau-mcp

Active·★ 348·Apache-2.0·Updated 2026-10-08

★ API Integration★ Data Processing

Tableau MCP is the official Model Context Protocol server from Tableau. It is described as a suite of developer primitives (tools, resources and prompts) that make it easier to build AI applications that integrate with Tableau Cloud and Tableau Server. Full documentation is hosted on the project's GitHub Pages site.

The README's example prompts show the intent: ask a published data source a question in plain language (top five states by sales in 2025 from the Superstore data), explore content (find the most viewed workbook in the last year, with owner, project, view count and last-modified date), and retrieve an image of a named view. Setup needs Node.js 22.7.5 or newer and an MCP client such as Claude Desktop, Cursor, VS Code or MCP Inspector, and the standard config runs `npx -y @tableau/mcp-server@latest` with your server URL, site name and a personal access token. A Deploy to Heroku button is also provided.

#Tableau#AI Integration#Developer Tools#Prompt Engineering#Data Analytics#Node.js#API Client

Features

01Querying Tableau Data with natural language

02Exploring Tableau Content (e.g., finding workbooks)

03Retrieving Tableau Views as images

04Facilitating AI Application Development for Tableau

Why choose it

+Official server from Tableau, so it follows the product's own concepts and documentation.

+Supports natural-language questions on published data sources, content exploration and fetching view images.

+Standard `npx` configuration works in most MCP clients, with a Heroku deploy option.

+Authenticates with a Tableau personal access token, so access follows the permissions of that account.

Trade-offs

!It requires a Tableau Cloud or Tableau Server deployment and a personal access token, so it is of no use without a Tableau account.

!Needs a recent Node.js (22.7.5 or newer).

!The README is brief and points to the separate documentation site for tool details and configuration options.

Compatibility

Node.js

Runtime

Verified via docs

MCP Clients

Integration Client

Verified via docs

Heroku

Deployment

Verified via docs

Tableau Server

Platform

Verified via docs

Quick start

$ npx -y @tableau/mcp-server@latest

Use cases

↳Analyzing sales data from Tableau datasources using natural language prompts

↳Discovering the most viewed or relevant Tableau workbooks/content

↳Displaying specific Tableau dashboard views via AI commands

↳Integrating AI models for advanced natural language interaction with Tableau environments

How it compares

≈vs a generic SQL or database MCP server: this one works through Tableau's published data sources and content, so answers follow Tableau's data model and permissions.

≈vs exporting Tableau data by hand to chat with it: the assistant queries the live data source instead of a static file.

Alternatives

Brave Search MCP★ 1.5k

Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.

awesome-mcp-servers★ 95.9k

A collection of MCP servers.

Context7★ 62.8k

MCP Server that provides up-to-date code documentation for LLMs and AI code editors.

GitHub MCP Server★ 33.5k

GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).

Gemini CLI★ 107.3k

An open-source AI agent that brings the power of Gemini directly into your terminal. Supports native MCP.

CopilotKit★ 37.8k

React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic Frontend.

Flowise★ 55.5k

Visual builder for AI agents and LLM workflows. Discontinued: the repository was archived in August 2026 and the project reached end of life on August 31, 2026.

Figma-Context-MCP★ 16.0k

MCP server to provide Figma layout information to AI coding agents like Cursor

See all alternatives →

Comments

No comments yet. Be the first!

tableau-mcp

Active·★ 348·Apache-2.0·Updated 2026-10-08

★ API Integration★ Data Processing

#Tableau#AI Integration#Developer Tools#Prompt Engineering#Data Analytics#Node.js#API Client

Features

01Querying Tableau Data with natural language

02Exploring Tableau Content (e.g., finding workbooks)

03Retrieving Tableau Views as images

04Facilitating AI Application Development for Tableau

Why choose it

+Official server from Tableau, so it follows the product's own concepts and documentation.

+Supports natural-language questions on published data sources, content exploration and fetching view images.

+Standard `npx` configuration works in most MCP clients, with a Heroku deploy option.

+Authenticates with a Tableau personal access token, so access follows the permissions of that account.

Trade-offs

!It requires a Tableau Cloud or Tableau Server deployment and a personal access token, so it is of no use without a Tableau account.

!Needs a recent Node.js (22.7.5 or newer).

!The README is brief and points to the separate documentation site for tool details and configuration options.

Compatibility

Node.js

Runtime

Verified via docs

MCP Clients

Integration Client

Verified via docs

Heroku

Deployment

Verified via docs

Tableau Server

Platform

Verified via docs

Quick start

$ npx -y @tableau/mcp-server@latest

Use cases

↳Analyzing sales data from Tableau datasources using natural language prompts

↳Discovering the most viewed or relevant Tableau workbooks/content

↳Displaying specific Tableau dashboard views via AI commands

↳Integrating AI models for advanced natural language interaction with Tableau environments

How it compares

≈vs a generic SQL or database MCP server: this one works through Tableau's published data sources and content, so answers follow Tableau's data model and permissions.

≈vs exporting Tableau data by hand to chat with it: the assistant queries the live data source instead of a static file.