mcp-knowledge-mind
Verified Safeby oscarmarina
Overview
Provides a local RAG server for AI tools to index and search Markdown and PDF files from local folders and GitHub repositories using a hybrid search engine.
Installation
npx @blockquote-playground/mcp-knowledge-mindEnvironment Variables
- GITHUB_CLASSIC_TOKEN
Security Notes
The server is designed for local-first operation. It accesses local file paths provided by the user and uses `process.env.GITHUB_CLASSIC_TOKEN` for GitHub integration. There are no direct 'eval' calls or clear malicious patterns. The primary security considerations revolve around how the user secures their `GITHUB_CLASSIC_TOKEN` and ensures the server is not exposed to untrusted external input given its local file access capabilities. Logging to files in `SERVER_DIR` could potentially expose sensitive information if not properly managed, but for a personal knowledge server, this is usually acceptable.
Similar Servers
haiku.rag
Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling to provide hybrid search, intelligent QA, and multi-agent research over user-provided documents, accessible via CLI, Python API, Web App, TUI, or as an MCP server for AI assistants.
Context-Engine
Self-improving code search and context engine for IDEs and AI agents, providing hybrid semantic/lexical search, symbol graph navigation, and persistent memory.
mcp-local-rag
Provides a local, RAG-like web search tool for Large Language Models to retrieve current information and context.
flexible-graphrag
The Flexible GraphRAG MCP Server integrates document processing, knowledge graph building, hybrid search, and AI query capabilities via the Model Context Protocol (MCP) for clients like Claude Desktop and MCP Inspector.