mcp-local-rag
Verified Safeby shinpr
Overview
A privacy-first, local document search server that leverages semantic search for Model Context Protocol (MCP) clients.
Installation
npx -y mcp-local-ragSecurity Notes
The server is explicitly designed for privacy and local-only operation, with no external network requests made after the initial embedding model download. It implements robust path validation to prevent directory traversal attacks by restricting file access to the user-defined BASE_DIR. Configuration relies on environment variables with sensible defaults, avoiding hardcoded secrets. Error messages are designed to suppress stack traces in a production environment (NODE_ENV=production), enhancing security by not exposing internal details. The embedding model is sourced from HuggingFace's official repository, and its integrity is verifiable.
Similar Servers
haiku.rag
An opinionated agentic RAG system that uses LanceDB for vector storage, Pydantic AI for multi-agent workflows, and Docling for document processing, exposing its capabilities as MCP tools for AI assistants.
sparql-llm
This project provides tools for Large Language Model (LLM)-powered SPARQL query generation over specific knowledge graphs, including a chat interface for user interaction and a Model Context Protocol (MCP) server for tool exposure.
flexible-graphrag
The Flexible GraphRAG MCP Server provides a Model Context Protocol (MCP) interface for AI assistants (like Claude Desktop) to interact with a sophisticated RAG and GraphRAG system for document processing, knowledge graph auto-building, hybrid search, and AI Q&A.
rag-server-mcp
Provides Retrieval Augmented Generation (RAG) capabilities to Model Context Protocol (MCP) clients by indexing local project documents and retrieving relevant information for LLMs.