How to integrate Stormboard MCP with Autogen

This guide walks you through connecting Stormboard to AutoGen using the Composio tool router. By the end, you'll have a working Stormboard agent that can summarize all sticky notes on a board, add action items to a stormboard project, list team members assigned to a board through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Stormboard account through Composio's Stormboard MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Stormboard logoStormboard
Api Key

Stormboard is an online sticky note whiteboard for brainstorming and project collaboration. It helps teams organize ideas and run more productive meetings.

41 Tools

Introduction

This guide walks you through connecting Stormboard to AutoGen using the Composio tool router. By the end, you'll have a working Stormboard agent that can summarize all sticky notes on a board, add action items to a stormboard project, list team members assigned to a board through natural language commands.

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

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

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

The Stormboard MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Stormboard account. It provides structured and secure access so your agent can perform Stormboard operations on your behalf.

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

Supported Tools

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

Accept a Storm Invite

Tool to accept a Storm invitation and join the Storm.

Add a Favorite Star

Tool to add a favorite star to a Storm on the Dashboard.

Check Authentication

Tool to verify API key authentication validity.

Close a Storm

Tool to close an open Storm, making it read-only.

Create a Line Connector

Tool to create a line connector between two ideas.

Create a new chat message

Tool to create a new chat message in a Stormboard storm.

Create a New Storm

Tool to create a new Storm in Stormboard for interactive planning and collaboration.

Create a New Tag

Tool to create a new tag in a Storm without any data related to Ideas.

Create a New User

Tool to create a new user account in Stormboard.

Create an idea in Stormboard

Tool to create a new idea in an existing Stormboard storm.

Create Tag Data for an Idea

Tool to update tag data for an idea.

Decline a Storm Invite

Tool to decline a Storm invitation and remove it from your list.

Delete a Connector Between Ideas

Tool to delete a line connector between two ideas.

Delete a Specific Connector

Tool to delete a line connector using the connector ID.

Get Storm Details

Tool to retrieve detailed information about a specific Storm.

Duplicate a Storm

Tool to duplicate an existing Storm.

Get a list of connectors in a Storm

Tool to retrieve a list of connectors within a specific Storm.

Get a List of Ideas

Tool to retrieve all ideas from a Storm.

Get A List Of Participants

Tool to retrieve a list of all participants in a Storm.

Get A List Of Storms Invites

Tool to retrieve a list of storms that you have been invited to.

Get List of Tags in Storm

Tool to retrieve the list of tags that have been created in a Storm.

Get A List Of Your Storms

Tool to retrieve a list of storms from Stormboard.

Get Authentication Info

Tool to retrieve authentication information and API token for the authenticated user.

Get Chat Messages

Tool to retrieve a list of chat messages from a Stormboard storm.

Get Idea Data

Tool to retrieve detailed data and metadata for a specific idea.

Get Info About Your User

Tool to retrieve authenticated user profile information.

Get My Storm Access

Tool to check if the authenticated user has access to a Storm and retrieve their permission level.

Get Storm Template

Tool to retrieve template data for a Storm including all sections and subsections.

Get Tag Data For An Idea

Tool to retrieve tag data for a specific idea in Stormboard.

Get Unread Chat Messages

Tool to retrieve unread chat messages from a specific Storm.

Invite Participants to Storm

Tool to invite people to join a Storm by email.

Join a Storm

Tool to join a Storm using its ID and access key.

Mark Chat Messages as Read

Tool to mark all chat messages as read in a Storm.

Remove a Favorite Star

Tool to remove a favorite star from a Storm on the Dashboard.

Reopen a Storm

Tool to reopen a closed Storm.

Update a Line Connector

Tool to update a specific line connector between two ideas.

Update Notifications

Tool to update user notification preferences.

Update Section in Storm

Tool to update a section's title, description, and/or character in a Storm.

Update Storm Legend

Tool to update the color labels of the legend for a storm.

Update Your Profile

Tool to update your user profile information.

Verify Your Account

Tool to verify a Stormboard account using a verification code.

FAQ

Frequently asked questions

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

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

Start with Stormboard.It takes 30 seconds.

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

Start building