mcp-ragdocs
If you are the rightful owner of mcp-ragdocs 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 Model Context Protocol (MCP) server that enables semantic search and retrieval of documentation using a vector database (Qdrant).
MCP-Ragdocs is a server designed to facilitate semantic search and retrieval of documentation by leveraging a vector database, specifically Qdrant. It allows users to add documentation from URLs or local files and perform searches using natural language queries. The server integrates with embedding providers like Ollama and OpenAI to enhance search capabilities. It is particularly useful for developers and researchers who need to manage and search through extensive documentation efficiently. The server can be configured to work with different platforms, including Cline, Roo-Code, and Claude Desktop, making it versatile for various development environments. Installation is straightforward, requiring Node.js and Qdrant, and it supports both local and cloud-based Qdrant setups.
Features
- Add documentation from URLs or local files
- Store documentation in a vector database for semantic search
- Search through documentation using natural language
- List all documentation sources
Tools
add_documentation
Add a document from a URL to a RAG database
search_documentation
Search for stored documents
list_sources
List all currently stored document sources
