mcp-ragdoc-fork
0
The RAG Documentation MCP Server provides advanced tools for retrieving and processing documentation using vector search, facilitating AI assistants to enhance their responses with relevant information. It supports multiple sources and offers features like semantic search and real-time augmentation for large language models.
RAG Documentation MCP Server
An MCP server implementation designed for documentation retrieval and processing through vector search, enabling AI assistants to enhance responses with relevant context.
Features
- Vector-based documentation search and retrieval
- Support for multiple documentation sources
- Semantic search capabilities
- Automated documentation processing
- Real-time context augmentation for LLMs
Tools
- search_documentation: Search through stored documentation using natural language queries.
- list_sources: List all documentation sources indexed in the system.
- extract_urls: Extract and analyze URLs from a given webpage.
- remove_documentation: Permanently remove specific documentation sources.
- list_queue: List all URLs in the processing queue.
- run_queue: Process and index queued URLs.
- clear_queue: Clear all URLs from the processing queue.
Usage
- Enhance AI responses
- Build documentation-aware AI assistants
- Create context-aware tools for developers
- Implement semantic documentation search
- Augment existing knowledge bases
Configuration
Add to claude_desktop_config.json for usage with Claude Desktop to set environment variables like OPENAI_API_KEY and QDRANT_URL.
License
Licensed under the MIT License.