Version: Next

LangGraph Agent with MCP adapter

This example demonstrates how to build a LangGraph agent that connects to a local MCP server, then wraps the agent as a uAgent and registers it on Agentverse using uAgents-adapter for discovery and use by ASI:One LLM.

Overview

LangGraph agent connects to a local MCP server using langchain_mcp_adapters.
The agent is wrapped using uagents_adapter to become a uAgent.
The uAgent is registered on Agentverse, making it discoverable and callable by ASI:One LLM.

Example: Math MCP Server Integration

1. Create the Math MCP Server

math_server.py
from mcp.server.fastmcp import FastMCP

mcp = FastMCP("Math")

@mcp.tool()
def add(a: int, b: int) -> int:
    """Add two numbers"""
    return a + b

@mcp.tool()
def multiply(a: int, b: int) -> int:
    """Multiply two numbers"""
    return a * b

if __name__ == "__main__":
    mcp.run(transport="stdio")

2. Create and Register the LangGraph Agent

agent.py

import os
import time
from dotenv import load_dotenv

from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
import asyncio
from langchain_mcp_adapters.tools import load_mcp_tools
from langgraph.prebuilt import create_react_agent

from uagents_adapter import LangchainRegisterTool, cleanup_uagent
from uagents_adapter.langchain import AgentManager

# Load environment variables
load_dotenv()

# Set your API keys
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
API_TOKEN = os.getenv("AGENTVERSE_API_KEY")

# Initialize the model
model = ChatOpenAI(model="gpt-4o")

# Store the agent globally so it can be accessed by the wrapper function
agent = None

async def setup_math_agent():
    global agent
    
    print("Setting up math agent...")
    server_params = StdioServerParameters(
        command="python",
        args=["math_server.py"],
    )
    
    async with stdio_client(server_params) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()
            tools = await load_mcp_tools(session)
            agent = create_react_agent(model, tools)
            
            # Test the agent
            test_response = await agent.ainvoke({
                "messages": [HumanMessage(content="what's (3 + 5) x 12?")]
            })
            print(f"Test response: {test_response['messages'][-1].content}")
            
            # Keep the connection alive
            while True:
                await asyncio.sleep(1)

def main():
    # Initialize agent manager
    manager = AgentManager()
    
    # Create agent wrapper
    async def agent_func(x):
        response = await agent.ainvoke({"messages": [HumanMessage(content=x)]})
        return response["messages"][-1].content
    
    agent_wrapper = manager.create_agent_wrapper(agent_func)
    
    # Start the agent in background
    manager.start_agent(setup_math_agent)
    
    # Register with uAgents
    print("Registering math agent...")
    tool = LangchainRegisterTool()
    agent_info = tool.invoke(
        {
            "agent_obj": agent_wrapper,
            "name": "math_agent_langchain_mcp",
            "port": 8080,
            "description": "A math calculation agent",
            "api_token": API_TOKEN,
            "mailbox": True
        }
    )
    
    print(f"✅ Registered math agent: {agent_info}")
    
    try:
        manager.run_forever()
    except KeyboardInterrupt:
        print("🛑 Shutting down...")
        cleanup_uagent("math_agent")
        print("✅ Agent stopped.")

if __name__ == "__main__":
    main()

Getting Started

Set up environment variables in a .env file:

OPENAI_API_KEY=your_openai_api_key
AGENTVERSE_API_KEY=your_agentverse_api_key

Install dependencies:

pip install langchain-openai langgraph mcp langchain-mcp-adapters uagents-adapter python-dotenv

Create the files:
- Save the math server code as math_server.py
- Save the agent code as agent.py
Run the agent:
```
python agent.py
```
Test your agent by querying it from ASI:One LLM or the chat Agentverse UI.

Open your Agentverse account and goto local agents.

Click on your agent and Use the "Chat with Agent" button on your Agentverse agent page

Agent logs:

(venv) xyz@Fetchs-MacBook-Pro mcp-langgraph-test % python3 agent.py
Initializing agent...
Setting up math agent...
Processing request of type ListToolsRequest
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
Processing request of type CallToolRequest
Processing request of type CallToolRequest
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
Test response: \((3 + 5) \times 12 = 8 \times 12 = 96\).
Registering math agent...
INFO:     [math_agent_langchain_mcp]: Starting agent with address: agent1qdspvt6tm34n3dnau9yekp8f3axmhd0vsmacxy59q20enmtvfvn0uxrvg6m
INFO:     [math_agent_langchain_mcp]: Agent 'math_agent_langchain_mcp' started with address: agent1qdspvt6tm34n3dnau9yekp8f3axmhd0vsmacxy59q20enmtvfvn0uxrvg6m
INFO:     [math_agent_langchain_mcp]: Agent inspector available at https://agentverse.ai/inspect/?uri=http%3A//127.0.0.1%3A8080&address=agent1qdspvt6tm34n3dnau9yekp8f3axmhd0vsmacxy59q20enmtvfvn0uxrvg6m
INFO:     [math_agent_langchain_mcp]: Starting server on http://0.0.0.0:8080 (Press CTRL+C to quit)
INFO:     [math_agent_langchain_mcp]: Starting mailbox client for https://agentverse.ai
INFO:     [math_agent_langchain_mcp]: Mailbox access token acquired
INFO:     [uagents.registration]: Registration on Almanac API successful
WARNING:  [uagents.registration]: Mismatch in almanac contract versions: supported (2.1.0), deployed (2.3.0). Update uAgents to the latest version for compatibility.
INFO:     [uagents.registration]: Almanac contract registration is up to date!
✅ Registered math agent: Created uAgent 'math_agent_langchain_mcp' with address agent1qdspvt6tm34n3dnau9yekp8f3axmhd0vsmacxy59q20enmtvfvn0uxrvg6m on port 8080
Connecting agent 'math_agent_langchain_mcp' to Agentverse...
INFO:     [mailbox]: Successfully registered as mailbox agent in Agentverse
Successfully connected agent 'math_agent_langchain_mcp' to Agentverse
Updating agent 'math_agent_langchain_mcp' README on Agentverse...
Successfully updated agent 'math_agent_langchain_mcp' README on Agentverse
INFO:     [math_agent_langchain_mcp]: Got a message from agent1qwy49pqq7zpg0d2ygv72wdr05vf4kuzc80lmnr9zev6h7vkdq3dk74rdxuq
INFO:     [math_agent_langchain_mcp]: Got a text message from agent1qwy49pqq7zpg0d2ygv72wdr05vf4kuzc80lmnr9zev6h7vkdq3dk74rdxuq: can you do calculation 7 + 9 - 8 * 6 + 89 - 6 + 9 * 10 ?
INFO:     [math_agent_langchain_mcp]: Sending structured output prompt to {'title': 'QueryMessage', 'type': 'object', 'properties': {'query': {'title': 'Query', 'type': 'string'}}, 'required': ['query']}
INFO:     [math_agent_langchain_mcp]: Sent structured output prompt to agent1q0h70caed8ax769shpemapzkyk65uscw4xwk6dc4t3emvp5jdcvqs9xs32y
INFO:     [math_agent_langchain_mcp]: Received structured output response from agent1q0h70caed8ax769shpemapzkyk65uscw4xwk6dc4t3emvp5jdcvqs9xs32y: 7 + 9 - 8 * 6 + 89 - 6 + 9 * 10 = ?
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
Processing request of type CallToolRequest
Processing request of type CallToolRequest
Processing request of type CallToolRequest
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
Processing request of type CallToolRequest
Processing request of type CallToolRequest
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
Processing request of type CallToolRequest
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"

note

Note: This example demonstrates a simple math agent, but you can extend it to use multiple MCP servers. For more advanced examples, check out:

Multi-Server Agent - Shows how to connect to multiple MCP servers (math and weather) using MultiServerMCPClient.

Overview​

Example: Math MCP Server Integration​

1. Create the Math MCP Server​

2. Create and Register the LangGraph Agent​

Getting Started​

Overview

Example: Math MCP Server Integration

1. Create the Math MCP Server

2. Create and Register the LangGraph Agent

Getting Started