MCP.so
Sign In

test-tableau-mcp

@joeconstantino

Repository

About test-tableau-mcp

a quick POC to expose Tableau VDS endpoints through an MCP server and integrate them with Claude Desktop client

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "vds": {
      "command": "uv",
      "args": [
        "--directory",
        "/ABSOLUTE/PATH/TO/PARENT/FOLDER/test-tableau-mcp/",
        "run",
        "vds.py"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is test-tableau-mcp?

test-tableau-mcp is a prototype MCP server that exposes Tableau VDS endpoints as tools for Claude Desktop. It allows querying Tableau data sources via the VDS API using natural language.

How to use test-tableau-mcp?

Set up a Python environment with UV, hardcode four variables (server URL, metadata GraphQL URL, datasource LUID, and session token) in vds.py, then run the server with uv --directory <ABSOLUTE PATH> run vds.py. Configure Claude Desktop by adding the server to its claude_desktop_config.json and restart the app.

Key features of test-tableau-mcp

  • Exposes Tableau VDS API as MCP tools.
  • Query data sources with fields, filters, sorts, and limits.
  • Integrates directly with Claude Desktop.
  • Supports in-context sample payloads for correct syntax.
  • Requires manual authentication via hardcoded session token.

Use cases of test-tableau-mcp

  • Querying sales data by segment or region through Claude Desktop.
  • Filtering and sorting Tableau VDS measures with natural language.
  • Prototyping MCP-based access to Tableau virtual connections.
  • Demonstrating VDS API query formatting with in-context examples.

FAQ from test-tableau-mcp

What are the system requirements?

Python 3.10 or higher, MCP SDK 1.2.0 or higher, and UV installed.

How do I configure the required environment variables?

Hardcode four variables in vds.py: VIZQL_API_BASE, METADATA_GRAPHQL, DS_LUID, and AUTH_TOKEN.

How do I run the server?

Use uv --directory <ABSOLUTE PATH TO PROJECT> run vds.py.

How do I connect test-tableau-mcp to Claude Desktop?

Add a server entry with command uv, arguments ["--directory", "/ABSOLUTE/PATH/", "run", "vds.py"] in Claude Desktop's claude_desktop_config.json.

How do I query the VDS API through the server?

Start by passing in-context samples from samples.py to teach Claude the correct Query object syntax for fields, filters, sorts, and limits.

Frequently asked questions

What are the system requirements?

Python 3.10 or higher, MCP SDK 1.2.0 or higher, and UV installed.

How do I configure the required environment variables?

Hardcode four variables in vds.py: `VIZQL_API_BASE`, `METADATA_GRAPHQL`, `DS_LUID`, and `AUTH_TOKEN`.

How do I run the server?

Use `uv --directory <ABSOLUTE PATH TO PROJECT> run vds.py`.

How do I connect test-tableau-mcp to Claude Desktop?

Add a server entry with command `uv`, arguments `["--directory", "/ABSOLUTE/PATH/", "run", "vds.py"]` in Claude Desktop's `claude_desktop_config.json`.

How do I query the VDS API through the server?

Start by passing in-context samples from `samples.py` to teach Claude the correct `Query` object syntax for fields, filters, sorts, and limits.

Comments

Basic information

Category

Data & Analytics

License

Apache-2.0

Transports

stdio

Author

joeconstantino

More Data & Analytics MCP servers

Jitsu

Jitsu

Jitsu is an open-source Customer Data Platform — an MIT-licensed alternative to Segment. This MCP server gives your AI assistant direct control over a Jitsu workspace, so you can run and debug data pipelines in conversat

Minds: Synthetic Market Research Panels

Minds

Minds is a synthetic market research platform. This MCP server lets ChatGPT, Claude, and Cursor run customer research end to end without leaving the assistant. Describe an audience in a brief ("German Gen Z grocery shopp

CryptoStruct Market Data

cryptostruct

Remote MCP server for historical crypto & prediction-market data: search ~500K instruments, live market stats (OHLC, turnover, spreads, depth, slippage), free sample files, and tick-data. Keyless for catalog & stats; opt

Opinly

Track competitors, rankings, and how AI answers rank you — then write and publish the fix.

CoinLobster

CoinLobster

The only MCP server with live whale trades across 15 exchanges plus on-chain DEX flow. Smart Money Radar, real liquidations and outcome-scored signals. No API key required.

3