arabold_docs-mcp-server
0
The docs-mcp-server is a Model Context Protocol (MCP) server designed to scrape, process, index, and search documentation for software libraries. It handles jobs asynchronously and uses advanced search techniques to provide efficient access to library documentation.
docs-mcp-server MCP Server
A MCP server for fetching and searching 3rd party package documentation. The project provides a Model Context Protocol (MCP) server that scrapes, indexes, and searches documentation for various software libraries. It uses OpenAI for vector embeddings and stores data in an SQLite database for efficient search. It supports multiple tools for managing jobs and searching documentation, and it can be built and run locally or using Docker.
Features
- Start, check status, list, or cancel scraping jobs
- Search documentation
- List and manage indexed libraries and versions
Installation
- Clone the repository
- Install Node.js dependencies and build the project
Running with Docker
- Build a Docker image and run the container
- Expose API endpoints for communication
CLI Usage
- Scrape and index from URLs
- Search for documentation
- Manage indexed libraries
Development
- Follow the project's architecture in , largely generated by AI assistant Cline.
Releasing
- Automate release process using semantic-release and Conventional Commits.