LangChain Integration

pip install langchain-mcp-adapters langchain-openai langchain

import os
import asyncio
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
from langchain.agents import create_agent

async def main():
    mcp_client = MultiServerMCPClient({
        "gdelt-cloud": {
            "transport": "streamable_http",
            "url": "https://gdelt-cloud-mcp.fastmcp.app/mcp",
            "headers": {
                "Authorization": f"Bearer {os.environ['GDELT_API_KEY']}"
            },
        }
    })

    tools = await mcp_client.get_tools(server_name="gdelt-cloud")
    messages = await mcp_client.get_prompt("gdelt-cloud", "gdelt_system_prompt")
    gdelt_prompt = "\n\n".join(str(msg.content) for msg in messages)

    agent = create_agent(
        model=ChatOpenAI(model="gpt-5.4-mini", temperature=0),
        tools=tools,
        system_prompt=gdelt_prompt,
    )

    result = await agent.ainvoke({
        "messages": [{
            "role": "user",
            "content": "Show protests in India by day over the past month, then drill into the most significant recent Events."
        }]
    })
    print(result["messages"][-1].content)

asyncio.run(main())

Show protests in India by day over the past month. Give a short analyst read and cite GDELT Cloud records.

Find new data center projects in Asia. Use Stories first, then structured infrastructure Events if available.

What are the fatal conflict Events in Lebanon this week? Keep it concise and cite evidence.

Assess sanctions and market implications from the latest Red Sea shipping signals. Start with GDELT, then use macro-finance and prediction markets if useful.