Back to Home
luisrodriguesphd icon

mcp-rag-agent

Verified Safe

by luisrodriguesphd

Overview

A RAG-based agent that answers questions about internal policies using semantic search via MongoDB Atlas Vector Search and OpenAI embeddings, with automated RAGAS-based evaluation.

Installation

Run Command
python -m mcp_rag_agent.mcp_server.server

Environment Variables

  • MONGODB_ATLAS_CLUSTER_URI
  • MONGODB_ATLAS_DB_NAME
  • OPENAI_API_KEY

Security Notes

The project follows good practices by using environment variables for API keys and sensitive configurations, preventing hardcoded secrets. No obvious malicious patterns like 'eval' or direct shell command injection (outside of the controlled 'start.sh' setup script) are present. The MCP server's ability to execute commands is tied to trusted internal modules, which is a standard pattern for such frameworks. Reliance on external APIs (OpenAI, MongoDB) introduces inherent network security considerations.

Similar Servers

Stats

Interest Score55
Security Score9
Cost ClassHigh
Avg Tokens3000
Stars1
Forks0
Last Update2025-11-30

Tags

RAGAI AgentSemantic SearchMongoDB AtlasLLM