Custom-Mcp-with-Agno
Verified Safeby Ashrokss
Overview
Develop a custom Model Context Protocol (MCP) server and client using the Agno agent framework to integrate custom tools like web search into AI agents.
Installation
python mcp_client.pyEnvironment Variables
- GROQ_API_KEY
- SERPER_API_KEY
Security Notes
The primary security risk lies in the explicit instruction to directly embed `GROQ_API_KEY` and `SERPER_API_KEY` into `config/config.py`. If this file is committed to a public repository, these sensitive API keys will be exposed. Users must manually ensure this file is not tracked by Git or use a more secure secrets management method. The `mcp_server.py` makes external HTTP requests using `httpx` to the Serper API, handling standard network communication. No `eval` or obfuscation is found. The client directly executes `python mcp_server.py` as a subprocess to start the tool server, which is safe in this controlled context, but generally highlights command execution capabilities.
Similar Servers
agentor
Build and deploy scalable AI agents that can interact with various tools and communicate via A2A and MCP protocols.
zeromcp
A minimal, pure Python Model Context Protocol (MCP) server for exposing tools, resources, and prompts via HTTP/SSE and Stdio transports.
End-to-End-Agentic-Ai-Automation-Lab
This MCP Server provides an API gateway for an AutoGen multi-agent system to interact with Notion via the Model Context Protocol (MCP), enabling AI-driven automation of Notion tasks and public exposure through ngrok.
mmcp
Manages Model Context Protocol (MCP) server definitions in a central configuration and applies them to various AI agent tools.