How to integrate Monday MCP with Autogen

This guide walks you through connecting Monday to AutoGen using the Composio tool router. By the end, you'll have a working Monday agent that can create a new project board for q3, add users to the design review board, archive completed tasks from last week through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Monday account through Composio's Monday MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Monday logoMonday
Oauth2

Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time.

121 Tools

Introduction

This guide walks you through connecting Monday to AutoGen using the Composio tool router. By the end, you'll have a working Monday agent that can create a new project board for q3, add users to the design review board, archive completed tasks from last week through natural language commands.

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

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

Also integrate Monday with

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

The Monday MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Monday.com workspace. It provides structured and secure access to your boards, items, and workflows, so your agent can perform actions like creating items, managing boards, updating columns, and organizing groups on your behalf.

  • Automated board and item management: Effortlessly create new boards, add items to existing boards, and archive or delete items as your projects evolve.
  • Dynamic column and group organization: Let your agent create, update, or remove columns and groups to keep your boards tailored to your team's needs.
  • Collaborative user and role administration: Add users to boards and assign roles, ensuring the right people have access and permissions for every project.
  • Streamlined workflow customization: Change column values, assign statuses or dropdowns, and create groups to match your workflow requirements in real time.
  • Efficient cleanup and restructuring: Archive or permanently delete boards, columns, or groups when they're no longer needed, keeping your workspace organized and clutter-free.

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

Supported Tools

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

Get account trigger statistics

Tool to retrieve statistics about account-level triggers and automations.

Activate users

Tool to activate or reactivate users in a Monday.

Add subscribers to object

Tool to add subscribers or owners to a monday.

Add teams to board

Tool to add teams to a Monday.

Add users to board

Adds users to a Monday.

Add users to team

Tool to add users to a Monday.

Add users to workspace

Tool to add one or more users to a workspace.

Aggregate board data

Tool to aggregate data across Monday.

Get app subscription

Tool to retrieve current app subscription data for the account.

Archive board

Archives a specified, existing, and unarchived board in Monday.

Archive item

Archives an existing Monday.

Archive object

Archives a Monday.

Archive workspace

Tool to archive a Monday.

Get audit logs

Tool to retrieve detailed security-related activity records for a Monday.

Get document blocks

Tool to retrieve document block data from workdocs via the API.

Get boards

Tool to retrieve board data via the Monday.

Change simple column value

Changes a specific column's value for a Monday.

Get board columns

Tool to retrieve column metadata from boards via the GraphQL API.

Get connection board IDs

Tool to retrieve board IDs associated with connection columns.

Get connections

Tool to retrieve connection data for integrations with external services.

Connect project to portfolio

Links an existing project board to a portfolio board for centralized management.

Convert board to project

Converts a regular Monday.

Create a Monday board

Creates a Monday.

Create column

Creates a new column with a specified type and title on a monday.

Create custom activity

Tool to create a custom activity in the Monday.

Create a Monday dashboard

Tool to create a Monday.

Create doc

Tool to create a new doc in Monday.

Create a folder

Tool to create a new folder in a Monday.

Create group

Creates a new group with the given `group_name` on an existing Monday.

Create item

Creates a new item on a Monday.

Create Item From Natural Language

Creates a new item on a Monday.

Create notification

Tool to send a notification to a user.

Create object

Tool to create any Monday.

Create tag

Tool to create a new tag or return an existing tag.

Create timeline item

Tool to create a new timeline item in the Emails & Activities app on a Monday.

Create update

Tool to create a new update for an item or reply to an existing update.

Invite and create a Monday user

Tool to invite and create a new user.

Create a Monday workspace

Tool to create a Monday.

Get custom activity

Tool to retrieve custom activity data from the Emails & Activities app.

Deactivate users

Tool to deactivate users from a monday.

Delete asset

Tool to remove uploaded files.

Delete board

Tool to permanently delete a board from your Monday.

Delete column

Deletes a specified column from a Monday.

Delete Custom Activity

Tool to delete a custom activity from the Emails & Activities app.

Delete doc

Tool to delete a Monday.

Delete folder

Tool to permanently delete a folder and all its contents from a Monday.

Delete group

Permanently deletes an existing group (and its items) from an existing board in Monday.

Delete item

Permanently deletes an existing Monday.

Delete object

Tool to permanently delete a Monday.

Delete subscribers from board

Tool to remove subscribers from a Monday.

Delete tag

Tool to remove a tag from an item in Monday.

Delete team

Tool to delete an existing team; use when you need to permanently remove a team by its ID after confirming it’s no longer needed.

Delete teams from board

Tool to remove teams from a board; use when you need to revoke team access to a specific board.

Delete teams from workspace

Tool to remove teams from a workspace.

Delete timeline item

Tool to delete a timeline item from the Emails & Activities app.

Delete update

Tool to delete an update by its ID.

Delete workspace

Tool to permanently delete a workspace by its ID.

Retrieve Monday docs

Tool to retrieve Monday.

Duplicate board

Tool to duplicate a Monday.

Duplicate item

Duplicates an item on a Monday.

Edit update

Tool to modify the text content of an existing update on an item.

Get account info

Retrieve account metadata and settings for the authenticated Monday.

Get board activity logs

Tool to retrieve activity logs from a specific Monday.

Get API version

Tool to retrieve the Monday.

Get assets

Tool to retrieve file/asset metadata from monday.

Get board views

Tool to retrieve board view data via GraphQL API.

Get favorites

Tool to retrieve all favorited items for the authenticated user.

Get folders

Tool to retrieve folder data from workspaces with filtering and pagination options.

Get form details

Tool to retrieve form metadata via the API using the form's unique token from the URL.

Get items by IDs

Tool to retrieve specific items by their IDs from Monday.

Get current user

Tool to fetch the current authenticated user's profile and permissions.

Get mutation complexity

Tool to get complexity data of mutations in Monday.

Get query complexity

Tool to retrieve complexity data and cost metrics for Monday.

Get tags

Tool to retrieve tags from the account.

Get teams

Tool to retrieve teams from Monday.

Get update replies

Retrieves updates and their replies for a specific Monday.

Get item updates

Tool to retrieve updates for a specific item.

Get API versions

Tool to retrieve data about available API versions.

Get view schema by type

Tool to retrieve type-specific board view configuration schemas via GraphQL API.

Get webhooks

Tool to retrieve webhooks for a board.

Get workspaces

Tool to retrieve workspaces.

Import doc from HTML

Tool to import HTML content into a new Monday.

Get items page

Tool to retrieve items from a Monday.

Like update

Tool to like an update on an item.

List groups

Tool to retrieve all groups of a specified board.

List items

Retrieves specified subitems from Monday.

List items by column values

Tool to search for items on a Monday.

List subitems by parent

Tool to retrieve subitems nested under parent items via GraphQL API.

List team members

Tool to list members of a specified team.

List users

Retrieves a list of users from Monday.

Move item to board

Moves a Monday.

Move item to group

Moves an item to a different group on the same Monday.

Query board mute settings

Tool to query a board's notification mute settings.

Pin update to top

Tool to pin an update to the top of an item.

Publish object

Tool to publish a Monday.

Query dashboards

Tool to query dashboards via Monday.

Query sprints

Tool to query sprint data for agile project management from Monday.

Remove users from team

Tool to remove users from a Monday.

Remove users from workspace

Tool to remove users from a workspace.

Set board permission

Sets or updates a board's default role and permissions.

Get item timeline

Tool to retrieve an item's Email & Activities (E&A) timeline data from Monday.

Get timeline item

Tool to retrieve a specific timeline item from the Emails & Activities app by ID.

Unlike update

Tool to remove a like from an update on an item.

Unpin update from top

Tool to unpin an update from the top of an item.

Unpublish object

Unpublish a Monday.

Update board

Updates a specified attribute of an existing board on Monday.

Update board hierarchy

Updates a board's position, workspace, or product in Monday.

Update column

Tool to update column title or description.

Update a doc

Tool to update a doc's title or append markdown content.

Update email domain

Tool to update users' email domains.

Update a Monday folder

Tool to update a Monday.

Update group

Tool to update an existing group on a board.

Update item

Tool to update an existing item's column value on Monday.

Update multiple users

Tool to update one or multiple users' attributes on Monday.

Update mute board settings

Tool to update a board's notification mute settings.

Update tag

Tool to return a tag's details or best-effort "rename" by creating or getting a tag with the requested name.

Update team

Tool to update a team's details in Monday.

Update users role

Tool to update users' roles to custom or default roles.

Update a Monday workspace

Tool to update a Monday.

Upload Asset

Tool to upload a file to an update or file column.

Get user connections

Tool to query user-specific connection data from Monday.

FAQ

Frequently asked questions

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

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

Start with Monday.It takes 30 seconds.

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

Start building