Docs RAG
Summary
This MCP server implements a Retrieval-Augmented Generation (RAG) system for documents stored in a local directory, enabling AI assistants to query and interact with Git repositories and text files. Built with TypeScript and leveraging LlamaIndex with Google's Gemini embeddings, it provides tools for listing documents, performing RAG queries against document collections, and adding new content through Git repository cloning or text file downloads. The server requires a Gemini API key for document indexing and querying, and is designed for integration with Claude Desktop, making it ideal for users who need to reference and analyze documentation, code repositories, or text collections during conversations with AI assistants.
Available Actions(4)
list_documents
List all available documents in the DOCS_PATH directory. Returns a formatted list of all documents and shows the total number of available documents.
rag_query
Query documents using RAG. Takes document_id and query as parameters, and returns AI-generated responses with context from documents.
add_git_repository
Clone a Git repository to the docs directory with optional sparse checkout. Takes repository_url as parameter. Optional parameters include document_name to customize the name of the document and subdirectory for sparse checkout of specific directories. Automatically pulls latest changes if repository already exists.
add_text_file
Download a text file to the docs directory. Takes file_url as parameter and uses wget to download the file.
社区评论
暂无评论. 成为第一个评论的人！
登录以参与讨论
