Back to Home
gauravsingh8026 icon

fastmcp-example

Verified Safe

by gauravsingh8026

Overview

This project demonstrates building an AI agent workflow using an MCP (Model Context Protocol) server, integrating LangChain for tool usage, and LangGraph for multi-step orchestration.

Installation

Run Command
python server.py

Environment Variables

  • TAVILY_API_KEY
  • OPENAI_API_KEY

Security Notes

The `http_request` tool (available both server-side via MCP and client-side via custom tools) allows making arbitrary HTTP requests. If an AI agent has unconstrained access to this tool, it could potentially be prompted to perform Server-Side Request Forgery (SSRF) to internal networks, Denial of Service (DoS) attacks, or interact with sensitive external APIs. The code does not include explicit URL allow-listing or advanced input sanitization for these network operations. No `eval` or similar direct code execution vulnerabilities were found, and API keys are managed via environment variables.

Similar Servers

Stats

Interest Score39
Security Score6
Cost ClassMedium
Avg Tokens1500
Stars2
Forks1
Last Update2025-12-09

Tags

AI AgentsLangChainLangGraphMCPWorkflow Automation