Skip to main content

Tableau MCP Server

A Model Context Protocol (MCP) server that enables AI agents to generate Tableau workbooks programmatically.

Installation Note: This package is distributed with an automated installer. Download the distribution package from GitHub and run the included install.bat script for easy setup.

What is this MCP?

This MCP server provides AI agents with the ability to:

  • Generate complete Tableau workbook (.twb) files
  • Create visualizations (bar charts, line charts, scatter plots, etc.)
  • Configure data connections and worksheets
  • Apply filters, sorting, and formatting
  • Build dashboards with multiple visualizations

How to use

Installation

  1. Download the distribution package from the GitHub repository
  2. Extract the files and navigate to the distribute folder
  3. Run install.bat (Windows) - this will:
    • Install the package from PyPI automatically
    • Set up the environment in your AppData folder
    • Configure the launcher scripts

MCP Server Configuration

After installation, add this to your Claude Desktop configuration:

{
  "mcpServers": {
    "tableau-mcp": {
      "command": "C:\\Users\\YourUsername\\AppData\\Roaming\\tableau-mcp\\tableau-mcp.bat",
      "env": {
        "GEMINI_API_KEY": "YOUR_KEY_HERE",
        "DEFAULT_LLM_PROVIDER": "gemini"
      }
    }
  }
}

Note: Get your free Gemini API key at https://aistudio.google.com/apikey

Available Tools

  • generate_tableau_workbook: Create complete Tableau workbooks with visualizations
  • profile_data_schema: Analyze CSV data structure for optimal visualization recommendations
  • get_sample_datasets: Access built-in sample datasets for testing

Basic Usage

Once connected, you can ask your AI agent to:

  • "Create a bar chart showing sales by region using my CSV data"
  • "Generate a dashboard with multiple visualizations"
  • "Build a time series chart with filtering capabilities"

The MCP will generate ready-to-use Tableau workbook files that can be opened directly in Tableau Desktop or published to Tableau Server.

Requirements

  • Windows OS (installer provided)
  • Python 3.9+
  • Gemini API key (free from Google AI Studio)
  • Compatible with Claude Desktop and other MCP clients
  • Generated workbooks work with Tableau Desktop 2020.1+

Distribution Package

The complete distribution package includes:

  • Automated installation script (install.bat)
  • Environment setup and dependency management
  • Ready-to-use launcher scripts
  • Full documentation and examples

Download from: https://github.com/kar10arora/TABLEAU_MCP

Metadata

Release files for tableau-mcp-kartik 1.0.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for tableau-mcp-kartik 1.0.5
File Interpreter ABI Platform
tableau_mcp_kartik-1.0.5-py3-none-any.whl Python 3 none any Details

Release files / tableau_mcp_kartik-1.0.5-py3-none-any.whl

Download URL tableau_mcp_kartik-1.0.5-py3-none-any.whl
Size 33.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7f7e2c771b5d226941b9975718727997fed8d3a6bbf888a51ecc64a30d3149af
BLAKE2b-256 checksum
How to use checksums
e4b6f3460a79fa85bc93daa4938914e742c24a1639b61d8c926ec607bdda9d6e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.4

Release history Release notifications | RSS feed

This release

1.0.5 This release

1 release file

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page