Tableau MCP
Query governed Tableau data sources from AI agents
BestMCPTools
Tableau MCP
bestmcptools.org
Last verified: September 20, 2026
Maintenance status
ActiveHow to Install Tableau MCP
$npx -y @tableau/tableau-mcpRequires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.
Setup by client
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"tableau-mcp": {
"command": "npx",
"args": [
"-y",
"@tableau/tableau-mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"tableau-mcp": {
"command": "npx",
"args": [
"-y",
"@tableau/tableau-mcp"
]
}
}
}VS Code (.vscode/mcp.json)
{
"servers": {
"tableau-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@tableau/tableau-mcp"
]
}
}
}Claude Code (terminal)
claude mcp add tableau-mcp -- npx -y @tableau/tableau-mcpAdd any API keys or environment variables the server's README lists.
About Tableau MCP
Tableau's MCP server connects AI assistants to published data sources, workbooks and metadata, letting agents answer questions using the governed joins, filters and calculated fields your analysts maintain. To trace a dashboard number back to its models, connect dbt to Claude as well.
Tableau MCP is a Analytics & BI MCP server designed for developers and AI power users. It enables extending AI assistants with real-world capabilities by exposing a structured set of tools over the Model Context Protocol. Key capabilities include standards-based mcp server interface, works with claude, gpt, gemini, and other mcp clients, tool discovery and structured outputs, and structured tool calls that work cleanly inside an LLM context. It integrates with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client, and is best suited for developers and AI power users who need ai engineers wiring assistants into real tools.
Key Features
- analytics
- bi
- tableau
- data
- Standards-based MCP server interface
- Works with Claude, GPT, Gemini, and other MCP clients
Pricing
Free: from Free (Tableau licence required)
Pros & Cons
Pros
- Drop-in support across MCP-compatible AI clients
- Reduces prompt boilerplate by exposing concrete tool calls
- Active community and ongoing updates
Cons
- Requires an MCP-capable client to use
- Initial setup can require configuration
- Capability surface depends on what the underlying service exposes
Best For
- AI engineers wiring assistants into real tools
- Teams adopting MCP as an integration standard
- Power users who want more than chat
Our Take on Tableau MCP
Official Tableau server that keeps queries inside governed data sources, so answers respect existing permissions. Requires a Tableau licence, which limits it to teams already invested in the platform.