MCP.so
Sign In
Servers

test-tableau-mcp

@joeconstantino

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

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.

More from Data & Analytics