Brainwires/project-rag

3.3

If you are the rightful owner of project-rag and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

A Rust-based Model Context Protocol (MCP) server that provides AI assistants with powerful RAG (Retrieval-Augmented Generation) capabilities for understanding massive codebases.

Tools

Functions exposed to the LLM to take actions

index_codebase

Index a complete codebase directory, creating embeddings for all code files.

query_codebase

Perform semantic search across the indexed code, returning relevant code chunks with similarity scores.

get_statistics

Retrieve statistics about the indexed codebase, including file counts and language breakdown.

clear_index

Clear all indexed data, deleting the entire Qdrant collection.

incremental_update

Update only changed files, detecting new, modified, and deleted files.

search_by_filters

Conduct advanced searches with filters, such as file extensions and programming languages.