Back to Home
AbhilashPoshanagari icon

openAi_MCP_server

Verified Safe

by AbhilashPoshanagari

Overview

An MCP server that acts as an AI assistant providing RAG capabilities for deep research, interactive UI generation (tables, maps, forms, buttons), PostgreSQL database access with query validation, and handling long-running tasks. It features an integrated OAuth 2.0 authentication server and uses an LLM agent to orchestrate tools and responses.

Installation

Run Command
python rag_mcp_server.py

Environment Variables

  • REMOTE_MONGODB_SERVER
  • REMOTE_MONGODB_DB
  • REMOTE_MONGODB_COLLECTION
  • POSTGRE_SERVER
  • POSTGRE_PORT
  • POSTGRE_DB
  • POSTGRE_USERNAME
  • POSTGRE_PASSWORD
  • MCP_SERVER_NAME
  • MCP_HOST
  • MCP_PORT
  • SENTENCE_TRANSFORMER_MODEL_PATH
  • OPENAI_EMBEDDING_MODEL
  • OPENAI_API_KEY
  • NGROK_AUTHTOKEN

Security Notes

1. Hardcoded client_id ("demo_client") and client_secret ("demo_secret") in `rag_mcp_auth_server.py` are used for a demo client and should not be used in production environments. 2. `ast.literal_eval` is used in `map_layout_tool` and `RestApiHelper.safe_parse_features`. While safer than `eval`, it can still parse arbitrary Python literals and could potentially be exploited with carefully crafted inputs to consume excessive resources or lead to other unintended behaviors. 3. CORS is configured with `allow_origins=["*"]` in `rag_mcp_server.py`, which is insecure for production environments and should be restricted to specific trusted origins.

Similar Servers

Stats

Interest Score0
Security Score7
Cost ClassMedium
Avg Tokens1000
Stars0
Forks0
Last Update2025-12-01

Tags

MCP ServerAI AgentRAGLLM ToolsUI GenerationPostgreSQLOAuth 2.0FastAPIDatabase InteractionLong-running tasks