arabold_docs-mcp-server
If you are the rightful owner of arabold_docs-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A MCP server for fetching and searching 3rd party package documentation.
The docs-mcp-server is a Model Context Protocol (MCP) server designed to scrape, process, index, and search documentation for various software libraries and packages. It fetches content from specified URLs, splits it into meaningful chunks using semantic splitting techniques, generates vector embeddings using OpenAI, and stores the data in an SQLite database. The server utilizes `sqlite-vec` for efficient vector similarity search and FTS5 for full-text search capabilities, combining them for hybrid search results. It supports versioning, allowing documentation for different library versions (including unversioned content) to be stored and queried distinctly. The scraping process is managed by an asynchronous job queue (`PipelineManager`), allowing multiple scrape jobs to run concurrently.
Features
- Efficient vector similarity search using `sqlite-vec`.
- Full-text search capabilities with FTS5.
- Supports versioning for different library versions.
- Asynchronous job queue for concurrent scraping.
- Companion CLI for local management and interaction.
