Document Extractor
Extracts and stores documentation from Microsoft Learn and GitHub URLs into PocketBase, enabling powerful search and retrieval for AI agents.
关于
The Document Extractor is an MCP (Model Context Protocol) server designed to centralize and make accessible external documentation. It efficiently extracts content from popular platforms like Microsoft Learn and GitHub, parsing articles and files to capture rich metadata. This extracted information is then stored in a PocketBase instance, providing robust full-text search capabilities and persistent storage. By leveraging the latest MCP SDK features, it offers dynamic tool management, session handling, and multiple transport options, making it an ideal backend for AI assistants requiring up-to-date and searchable external knowledge.
主要功能
- Dynamic tool management with lazy loading and session management.
- 0 GitHub stars
- Preserves rich metadata, including word counts, source, and timestamps.
- Content extraction from Microsoft Learn articles and GitHub files.
- Persistent storage and full-text search via PocketBase integration.
- Supports multiple transport protocols: STDIO, Streamable HTTP, and SSE.
使用案例
- Building a searchable knowledge base from online documentation for AI assistants.
- Centralizing and indexing external documentation from Microsoft Learn and GitHub repositories.
- Providing AI agents with up-to-date and specific information extracted from web URLs.
