mcp-metabase-server and metabase-mcp
These two tools appear to be competing implementations of an MCP (presumably a "Metabase Control Plane" or similar) server designed to integrate with Metabase, potentially enabling LLM interaction with analytics data.
About mcp-metabase-server
easecloudio/mcp-metabase-server
A comprehensive MCP server for Metabase with 70+ tools.
Implements full CRUD operations and advanced features like dashboard subscriptions, permission management, and schema synchronization through 70+ MCP tools. Built in TypeScript, it connects AI assistants to Metabase v0.46+ (cloud or self-hosted) via the Model Context Protocol, supporting both API key and username/password authentication. Provides structured resource access through `metabase://` URIs alongside tools for analytics monitoring, user lifecycle management, and complex query execution with export capabilities.
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