r2r-mcp

# r2r-mcp **Model Context Protocol (MCP) server for R2R (RAG to Riches) retrieval system** This package provides a FastMCP server that connects to [R2R](https://github.com/SciPhi-AI/R2R) for advanced retrieval-augmented generation (RAG) capabilities. It enables AI assistants like Claude Desktop, Cursor, and other MCP clients to search, retrieve, and manage documents in R2R knowledge bases. ## Features - 🔍 **Semantic Search** - Vector-based and full-text search across documents - 🤖 **RAG Queries** - Retrieval-augmented generation with configurable LLM settings - 📝 **Document Management** - Upload, update, and list documents with upsert semantics - 🏷️ **Metadata Filtering** - Advanced filtering by tags, domain, and custom metadata - 🌐 **Environment-Based Config** - Zero configuration, reads from environment variables ## Installation ### Using uvx (recommended) The easiest way to use r2r-mcp is with `uvx`, which automatically handles installation: ```bash uvx r2r-mcp ``` ### Using pip Install globally or in a virtual environment: ```bash pip install r2r-mcp ``` Then run: ```bash r2r-mcp ``` ### As a Python Module You can also run it as a module: ```bash python -m r2r_mcp ``` ## Configuration The server automatically reads configuration from environment variables: | Variable | Description | Default | |----------|-------------|---------| | `R2R_API_BASE` or `R2R_BASE_URL` | R2R server URL | `http://localhost:7272` | | `R2R_COLLECTION` | Collection name for queries | Server default | | `R2R_API_KEY` | API key for authentication | None | ## Usage with MCP Clients ### Cursor IDE Add to `.cursor/mcp.json`: ```json { "mcpServers": { "KnowledgeBase": { "command": "uvx", "args": ["r2r-mcp"], "env": { "R2R_API_BASE": "http://localhost:7272", "R2R_COLLECTION": "aia-r1" } } } } ``` ### Claude Desktop Add to Claude Desktop configuration (`~/Library/Application Support/Claude/claude_desktop_config.jso…