metabase-mcp-server and metabase-mcp
The two tools are competitors, with "hluaguo/metabase-mcp" having a more detailed description of its intent to enable LLM interaction with analytics data via the Metabase API, while "CognitionAI/metabase-mcp-server" serves a similar, but less explicitly detailed, purpose as a Metabase MCP server.
About metabase-mcp-server
CognitionAI/metabase-mcp-server
Cognition's Metabase MCP Server
Exposes 81+ tools covering Metabase's full API surface—dashboards, cards, databases, tables, and collections—enabling AI assistants to query, execute, and manage analytics operations programmatically. Built as an MCP server with TypeScript and Node.js, it integrates seamlessly with Claude Desktop and Windsurf IDE via stdio transport, supporting flexible tool loading modes (essential, all, read-only, write-only) configured through environment variables and command-line flags.
About metabase-mcp
hluaguo/metabase-mcp
Metabase MCP server provides integration with the Metabase API, enabling LLM with MCP capabilites to directly interact with your analytics data, this server acts as a bridge between your analytics platform and conversational AI.
Implements a FastMCP server compatible with multiple transport protocols (STDIO, SSE, HTTP), supporting both SQL and MongoDB query execution with native parameter templating and aggregation pipeline support. Built on modern Python 3.12+ with context-aware logging middleware and proper error handling, it integrates directly with Claude Desktop, Cursor IDE, and any MCP-compliant client through environment-based API key or session authentication.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work