mcp-local-rag and repo-graphrag-mcp

mcp-local-rag
56
Established
repo-graphrag-mcp
36
Emerging
Maintenance 13/25
Adoption 10/25
Maturity 16/25
Community 17/25
Maintenance 10/25
Adoption 3/25
Maturity 9/25
Community 14/25
Stars: 118
Forks: 19
Downloads: —
Commits (30d): 0
Language: Python
License: MIT
Stars: 3
Forks: 3
Downloads: —
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About mcp-local-rag

nkapila6/mcp-local-rag

"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨

Implements multi-engine web search across 9+ backends (DuckDuckGo, Google, Bing, Brave, Wikipedia) with semantic ranking using Google's MediaPipe text embeddings, extracting markdown from fetched URLs without external APIs. Exposes tools like `deep_research`, `deep_research_google`, and `rag_search_ddgs` as MCP resources compatible with Claude Desktop, Cursor, and other MCP clients. Deployable via `uvx` or Docker and includes Agent Skills that guide LLMs on query formulation and backend selection for privacy-aware or comprehensive research.

About repo-graphrag-mcp

yumeiriowl/repo-graphrag-mcp

An MCP server that uses LightRAG and Tree-sitter to build a repository knowledge graph from code and docs, for Q&A and implementation planning.

Related comparisons

mcp-local-rag and knowledge-to-action-mcp mcp-local-rag and mcp-rag-server mcp-local-rag and mcp-rag-server mcp-local-rag and Real-time-web-search-RAG-with-MCP mcp-local-rag and supernova-mcp-rag mcp-local-rag and mcp-local-rag

Scores updated daily from GitHub, PyPI, and npm data. How scores work