MCP-DOC-Server-OpenRouter
The docs-mcp-server is a Model Context Protocol server designed to retrieve and search documentation for software libraries and packages by scraping content from various online sources. It features intelligent content processing, efficient storage, and hybrid search capabilities, facilitating quick and relevant documentation retrieval.
docs-mcp-server MCP Server
A MCP server for fetching and searching 3rd-party package documentation.
✨ Key Features
- 🌐 Versatile Scraping: Fetch documentation from diverse sources like websites, GitHub, npm, PyPI, or local files.
- 🧠 Intelligent Processing: Automatically split content semantically and generate embeddings using models (OpenAI, Google Gemini, etc.).
- 💾 Optimized Storage: Use SQLite with
sqlite-vecfor vector storage and FTS5 for full-text search. - 🔍 Powerful Hybrid Search: Combine vector similarity and full-text search across library versions.
- ⚙️ Asynchronous Job Handling: Manage tasks with a background job queue and MCP/CLI tools.
- 🐳 Simple Deployment: Deploy using Docker or npx.
Overview
This project provides a Model Context Protocol (MCP) server designed to scrape, process, index, and search documentation for software libraries and packages. It fetches content from specific URLs, splits it into meaningful chunks using semantic splitting, generates vector embeddings, and stores data in an SQLite database with hybrid search capabilities.