mcp-local-rag and knowledge-to-action-mcp
Both tools implement the MCP (Model Context Protocol) server for local RAG-like functionalities, making them ecosystem siblings within the GraphRAG and local context processing space, with one potentially offering a more primitive base and the other building upon that or offering more advanced agent-ready features for Obsidian.
About mcp-local-rag
nkapila6/mcp-local-rag
"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨
This tool helps large language models (LLMs) like Claude perform deep, up-to-date web research and answer questions using current information. It takes your natural language questions, searches across many web sources, extracts the most relevant details, and feeds them back to the LLM. Researchers, analysts, or anyone needing accurate, real-time information from an AI assistant would find this useful.
About knowledge-to-action-mcp
tac0de/knowledge-to-action-mcp
MCP server for Obsidian GraphRAG, agent-ready context, preview-only planning, and safe repo handoffs
Combines graph-aware note retrieval with optional embeddings-based semantic reranking to surface contextual neighbors, then structures results into agent-ready packets containing briefs, risks, and repo file hints. Implements preview-only action planning and bounded workspace inspection (ripgrep, git status) without exposing shell access, integrating via stdio with Claude, VS Code, and Cursor.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work