-
securityF
license-
qualityA TypeScript implementation of the MCP Agent framework, providing tools for building context-aware agents with advanced workflow management, logging, and execution capabilities.
Last updated -
9
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)
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
This server cannot be installed
local-only server
The server can only run on the client's local machine because it depends on local resources.
A modular production-ready system that provides specialized agents for math, research, weather, and summarization tasks through a unified MCP toolbox with smart supervisor capabilities.
Related MCP Servers
- AsecurityFlicenseAqualityAn MCP server that supercharges AI assistants with powerful tools for software development, enabling research, planning, code generation, and project scaffolding through natural language interaction.Last updated -1140TypeScript
- -securityFlicense-qualityAn advanced MCP server that implements sophisticated sequential thinking using a coordinated team of specialized AI agents (Planner, Researcher, Analyzer, Critic, Synthesizer) to deeply analyze problems and provide high-quality, structured reasoning.Last updated -124Python
- GoMIT License