Skip to main content
This guide shows you how to connect your LangChain agent to Caylex using the langchain-mcp-adapters package.

​
Prerequisites

​
Installation

pip install langchain-mcp-adapters langchain-openai langgraph

​
Full example

main.py
import asyncio
import os

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI


async def main() -> None:
    api_key = os.environ["CAYLEX_API_KEY"]
    user_email = os.environ["CAYLEX_USER_EMAIL"]

    # Connect to Caylex via MCP
    async with MultiServerMCPClient(
        {
            "caylex": {
                "transport": "streamable_http",
                "url": "https://proxy.caylex.ai/mcp",
                "headers": {
                    "x-api-key": api_key,
                    "x-user-email": user_email,
                },
            }
        }
    ) as client:
        # Get all available tools from Caylex
        tools = client.get_tools()

        # Create a ReAct agent with the tools
        model = ChatOpenAI(model="gpt-5.2")
        agent = create_react_agent(model, tools)

        # Run the agent
        response = await agent.ainvoke(
            {
                "messages": [
                    {
                        "role": "user",
                        "content": "Summarize my calendar for this week and draft follow-up emails for any meetings that need action items.",
                    }
                ]
            }
        )

        # Print the final response
        for message in response["messages"]:
            if message.type == "ai" and message.content:
                print(message.content)


asyncio.run(main())

​
Step-by-step

1

Set environment variables

export CAYLEX_API_KEY="ck_abc123.your-secret-key"
export CAYLEX_USER_EMAIL="user@example.com"
export OPENAI_API_KEY="your-openai-key"
2

Create the MCP client

Use MultiServerMCPClient with the Caylex endpoint and headers. The "streamable_http" transport is recommended.
async with MultiServerMCPClient(
    {
        "caylex": {
            "transport": "streamable_http",
            "url": "https://proxy.caylex.ai/mcp",
            "headers": {
                "x-api-key": api_key,
                "x-user-email": user_email,
            },
        }
    }
) as client:
    tools = client.get_tools()
3

Create an agent with the tools

Pass the Caylex tools to LangGraph’s create_react_agent or any LangChain agent constructor.
model = ChatOpenAI(model="gpt-5.2")
agent = create_react_agent(model, tools)
4

Run the agent

Invoke the agent with a user message.
response = await agent.ainvoke(
    {"messages": [{"role": "user", "content": "Your query here."}]}
)

​
Further reading