How to integrate Teamwork MCP with Autogen

This guide walks you through connecting Teamwork to AutoGen using the Composio tool router. By the end, you'll have a working Teamwork agent that can create tasks and tags, list your projects, update tasks, log time, and search your workspace through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Teamwork account through Composio's Teamwork MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Teamwork logoTeamwork
Api Key

Teamwork is a project management platform for planning projects, coordinating tasks, collaborating with teams, and tracking time. It helps teams keep client work, deadlines, workload, and billable hours organized in one place.

12 Tools

Introduction

This guide walks you through connecting Teamwork to AutoGen using the Composio tool router. By the end, you'll have a working Teamwork agent that can create tasks and tags, list your projects, update tasks, log time, and search your workspace through natural language commands.

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

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

Also integrate Teamwork with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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 Teamwork
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Teamwork tools
  • Run a live chat loop where you ask the agent to perform Teamwork 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 Teamwork MCP server, and what's possible with it?

The Teamwork MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Teamwork account. It provides structured and secure access to your projects, tasks, milestones, people, tags, and time entries, so your agent can plan work, coordinate assignments, track progress, log time, and find project information on your behalf.

  • Project and task discovery: Have your agent list and filter projects, task lists, and tasks by details such as status, assignee, dates, completion state, or tags.
  • Task creation and updates: Direct your agent to create tasks with schedules, assignments, estimates, privacy settings, and tags, or update selected details on existing tasks.
  • Milestone and team coordination: Let the agent find milestones by project, status, due date, assignee, or text, and list people available for assignment and ownership.
  • Time tracking: Instruct your agent to review time entries by project, task, person, date, billing state, or tags, and log time against tasks.
  • Search and organization: Have your agent search across Teamwork resources and create or list tags to keep work organized.

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 Teamwork 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 Teamwork 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 Teamwork 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 Teamwork session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["teamwork"]
    )
    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 Teamwork 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 Teamwork assistant agent with MCP tools
    agent = AssistantAgent(
        name="teamwork_assistant",
        description="An AI assistant that helps with Teamwork 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 Teamwork 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 Teamwork 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 Teamwork 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 Teamwork 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 Teamwork session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["teamwork"]
    )
    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 Teamwork assistant agent with MCP tools
        agent = AssistantAgent(
            name="teamwork_assistant",
            description="An AI assistant that helps with Teamwork 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 Teamwork 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 Teamwork 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 Teamwork, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

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

Create Tag

Create a Teamwork tag, or return the existing installation tag when the same name already exists.

Create Task

Create a task in a Teamwork task list with common scheduling, assignment, estimate, privacy, and tag fields.

List Milestones

List visible Teamwork milestones by project, status, due-date range, assignee, or text.

List People

List people visible to the connected Teamwork user for assignment and ownership workflows.

List Projects

List projects visible to the connected Teamwork user, with focused filters for name, status, company, membership, and archival state.

List Tags

List Teamwork tags visible to the connected user, optionally filtered by project, item type, name, or usage.

List Task Lists

List Teamwork task lists, usually within one or more projects, so an agent can place or locate tasks.

List Tasks

List and filter Teamwork tasks by project, task list, assignee, dates, completion state, or tags.

List Time Entries

List accessible Teamwork time entries by project, task, person, date range, billing state, or tags.

Log Time Entry

Log time against a Teamwork task with a date, duration, optional start time, description, person, billing state, and tags without changing task status.

Search Teamwork

Search across Teamwork projects, tasks, task lists, milestones, people, companies, time entries, and other supported item types.

Update Task

Update selected fields of an existing Teamwork task while leaving omitted task fields unchanged.

FRAMEWORKS

How to build Teamwork MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Teamwork MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Teamwork MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Teamwork MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Teamwork MCP with Claude Cowork

Codex logo

Codex

Use Teamwork MCP with Codex

OpenClaw logo

OpenClaw

Use Teamwork MCP with OpenClaw

Hermes logo

Hermes

Use Teamwork MCP with Hermes

CLI logo

CLI

Use Teamwork MCP with CLI

Google ADK logo

Google ADK

Use Teamwork MCP with Google ADK

LangChain logo

LangChain

Use Teamwork MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Teamwork MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Teamwork MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Teamwork MCP with LlamaIndex

CrewAI logo

CrewAI

Use Teamwork MCP with CrewAI

FAQ

Frequently asked questions

With a standalone Teamwork MCP server, the agents and LLMs can only access a fixed set of Teamwork tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Teamwork 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 Teamwork tools.

Yes, absolutely. You can configure which Teamwork 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 Teamwork data and credentials are handled as safely as possible.

Start with Teamwork.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies