SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Cursor MCP with Autogen

Connect Autogen to Cursor MCP. List all active cloud agents for this project, show recent code changes tracked by cursor, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Cursor logoCursor
Api Key

Cursor is an AI-powered code editor built on VSCode. It delivers smart, collaborative coding with integrated analytics and agent support.

5 Tools

Introduction

This guide walks you through connecting Cursor to AutoGen using the Composio tool router. By the end, you'll have a working Cursor agent that can list all active cloud agents for this project, show recent code changes tracked by cursor, summarize analytics for your team's workspace through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Cursor account through Composio's Cursor MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Cursor with

Claude CodeCursorChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKGrok BotCodexKimi CodeGrok BuildVS CodeOpenCodeOpenClawHermesAtomic AgentPiDeepSeek HarnessCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Cursor
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Cursor tools
  • Run a live chat loop where you ask the agent to perform Cursor operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Cursor MCP server, and what's possible with it?

The Cursor MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Cursor account. It provides structured and secure access to your Cloud Agents, accessible GitHub repositories, agent conversations, API key information, and available AI models, so your agent can list agents, review conversations, browse repositories, inspect API key details, and check available models on your behalf.

  • Cloud Agent overview: Have your agent list your Cursor Cloud Agents so you can quickly see which agents are available.
  • Agent conversation review: Let the agent retrieve a Cloud Agent's conversation history to help you understand its context and prior work.
  • Repository discovery: Direct your agent to list the GitHub repositories available through your authenticated Cursor account.
  • API key account details: Instruct your agent to check your API key name, creation date, and owner email when you need to verify access.
  • Model availability checks: Have your agent list the AI models currently available in Cursor before choosing one for a task.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Cursor account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Cursor via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Cursor connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Cursor session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["cursor"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Cursor tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Cursor assistant agent with MCP tools
    agent = AssistantAgent(
        name="cursor_assistant",
        description="An AI assistant that helps with Cursor operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Cursor tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Cursor related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Cursor tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Cursor and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Cursor session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["cursor"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Cursor assistant agent with MCP tools
        agent = AssistantAgent(
            name="cursor_assistant",
            description="An AI assistant that helps with Cursor operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Cursor related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Cursor through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Cursor, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Cursor action and event your agent gets out of the box.

Get Agent Conversation

Tool to retrieve the conversation history for a specific cloud agent.

Get API Key Info

Tool to retrieve API key information including the key name, creation date, and owner email.

List Agents

Tool to retrieve a paginated list of all Cursor Cloud agents.

List Available Models

Tool to retrieve the list of available AI models in Cursor.

List GitHub Repositories

Tool to list GitHub repositories accessible to the authenticated user.

FRAMEWORKS

How to build Cursor MCP Agent with another framework

Claude Code logo

Claude Code

Use Cursor MCP with Claude Code

Cursor logo

Cursor

Use Cursor MCP with Cursor

ChatGPT logo

ChatGPT

Use Cursor MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Cursor MCP with Claude Cowork

Antigravity logo

Antigravity

Use Cursor MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Cursor MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Cursor MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Cursor MCP with Grok Bot

Codex logo

Codex

Use Cursor MCP with Codex

Kimi Code logo

Kimi Code

Use Cursor MCP with Kimi Code

Grok Build logo

Grok Build

Use Cursor MCP with Grok Build

VS Code logo

VS Code

Use Cursor MCP with VS Code

OpenCode logo

OpenCode

Use Cursor MCP with OpenCode

OpenClaw logo

OpenClaw

Use Cursor MCP with OpenClaw

Hermes logo

Hermes

Use Cursor MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Cursor MCP with Atomic Agent

Pi logo

Pi

Use Cursor MCP with Pi

DeepSeek Harness logo

DeepSeek Harness

Use Cursor MCP with DeepSeek Harness

CLI logo

CLI

Use Cursor MCP with CLI

Google ADK logo

Google ADK

Use Cursor MCP with Google ADK

LangChain logo

LangChain

Use Cursor MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Cursor MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Cursor MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Cursor MCP with LlamaIndex

CrewAI logo

CrewAI

Use Cursor MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Cursor MCP with Pydantic AI

FAQ

Frequently asked questions

With a standalone Cursor MCP server, the agents and LLMs can only access a fixed set of Cursor tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Cursor and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Cursor tools.

Yes, absolutely. You can configure which Cursor scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Cursor data and credentials are handled as safely as possible.

Start with Cursor.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Cursor tool your agent needs.Free to start.

Start building