DOC-Server-MCP
The docs-mcp-server is a Model Context Protocol server designed for scraping, processing, and searching documentation of software libraries. It offers versatile scraping from various sources and supports intelligent processing with semantic splitting and embedding generation. It is optimized for efficient storage and hybrid search, making it a powerful tool for managing and querying library documentation.
docs-mcp-server MCP Server
A MCP server for fetching and searching 3rd party package documentation.
✨ Key Features
- Versatile scraping from diverse sources like websites, GitHub, npm, PyPI, or local files.
- Intelligent processing splitting content semantically and generating embeddings using models like OpenAI, Google Gemini, Azure OpenAI, AWS Bedrock, Ollama, etc.
- Optimized storage using SQLite with vector storage and robust full-text search.
- Hybrid search combining vector similarity and full-text search.
- Asynchronous job handling with a background job queue and MCP/CLI tools.
- Simple deployment via Docker or npx.
Overview
Provides an MCP server designed to scrape, process, index, and search documentation for software libraries and packages. Supports content fetching from URLs, semantic splitting, vector embeddings generation using OpenAI, and data storage in SQLite. Utilizes efficient vector similarity and full-text search capabilities for hybrid search results, supporting versioning for different library versions.