Memo-MCP
Verified Safeby milasd
Overview
Provides a local LLM Model Context Protocol (MCP) server for journaling with Retrieval-Augmented Generation (RAG) to search and retrieve personal memo and journal entries.
Installation
uv run memo-mcpEnvironment Variables
- MEMO_DATA_ROOT
- MEMO_USE_GPU
- MEMO_EMBEDDING_MODEL
- MEMO_RAG_LITE
- MEMO_QDRANT_HOST
- MEMO_QDRANT_PORT
- MEMO_QDRANT_API_KEY
Security Notes
The server is designed for local, personal use, communicating via standard I/O (stdio) with LLM clients. This greatly reduces network attack surface compared to a web-exposed service. Hardcoded secrets are not present; configurations like `qdrant_api_key` are optional environment variables and default to `None`. The use of `pickle.load` for FAISS and simple vector stores, while generally unsafe for untrusted data, is used here for self-generated, local persistence, which is a lower risk within the intended local application context. Privacy warnings are clearly stated for sensitive data when using external models. No 'eval' or obvious malicious patterns found.
Similar Servers
uLoopMCP
Acts as a bridge between Unity Editor and various LLM-powered development tools, enabling AI agents to compile, test, and operate Unity projects autonomously via the Model Context Protocol.
nanobanana-mcp-server
AI-powered image generation and editing using Google Gemini models (Flash and Pro) with intelligent model selection via Model Context Protocol.
seamless-agent
Enables AI agents, particularly GitHub Copilot, to perform interactive user confirmations and collect additional input within VS Code or Antigravity, ensuring user control over agent actions.
mcp
This MCP server advises development agents on modern and performant best practices by identifying inefficient or outdated npm packages and serving migration documentation.