Supports environment variable configuration through .env files for storing API keys and deployment information
Provides HTTP API endpoints that expose each agent's functionality through a server running on port 8000
Integrates with LangChain to build specialized agents for research, math, and meteorological tasks
Connects to Azure OpenAI deployments for powering the agents and tools through environment variables
Supports testing through pytest, allowing users to add tests in a tests/ directory
Includes a dedicated Wikipedia tool for retrieving and processing information from Wikipedia articles
Multi-Agent Tools Platform
This project provides a modular, production-ready agentic system for advanced math, research, weather, and summarization tasks, using FastMCP, LangChain, and FastAPI.
Features
Five core tools: Math, Search, Weather, Wikipedia, Summarizer (
tools_server.py)Three specialized agents: Research, Math, Meteo (
agents.py)HTTP API endpoints: FastAPI server exposes each agent (
api_servers.py)Unified MCP toolbox: Wraps APIs and provides a smart supervisor tool (
agent_tools.py)
Related MCP server: MCP-Add-Weather
Setup
1. Clone & Install
2. Environment Variables
Create a .env file or set these in your shell:
3. Run Components (in separate terminals)
The FastAPI server runs on http://127.0.0.1:8000
Use an MCP client to interact with the
supervisortool inagent_tools.py
File Structure
tools_server.py– Five tools, FastMCP serveragents.py– Three ReAct agents, using LangChain and FastMCPapi_servers.py– FastAPI server, exposes each agentagent_tools.py– MCP toolbox, API wrappers, supervisorrequirements.txt– All dependencies.env.example– Example environment file
Testing
You can add tests using pytest. Example test files can be placed in a tests/ directory.
License
MIT