How to integrate Stormboard MCP with Autogen

GET STARTED FOR FREE
Framework Integration Gradient
Stormboard Logo
AutoGen Logo
divider

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.

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.

Supported Tools & Triggers

Tools
Accept a Storm InviteTool to accept a Storm invitation and join the Storm.
Add a Favorite StarTool to add a favorite star to a Storm on the Dashboard.
Check AuthenticationTool to verify API key authentication validity.
Close a StormTool to close an open Storm, making it read-only.
Create a Line ConnectorTool to create a line connector between two ideas.
Create a new chat messageTool to create a new chat message in a Stormboard storm.
Create a New StormTool to create a new Storm in Stormboard for interactive planning and collaboration.
Create a New TagTool to create a new tag in a Storm without any data related to Ideas.
Create a New UserTool to create a new user account in Stormboard.
Create an idea in StormboardTool to create a new idea in an existing Stormboard storm.
Create Tag Data for an IdeaTool to update tag data for an idea.
Decline a Storm InviteTool to decline a Storm invitation and remove it from your list.
Delete a Connector Between IdeasTool to delete a line connector between two ideas.
Delete a Specific ConnectorTool to delete a line connector using the connector ID.
Get Storm DetailsTool to retrieve detailed information about a specific Storm.
Duplicate a StormTool to duplicate an existing Storm.
Get a list of connectors in a StormTool to retrieve a list of connectors within a specific Storm.
Get a List of IdeasTool to retrieve all ideas from a Storm.
Get A List Of ParticipantsTool to retrieve a list of all participants in a Storm.
Get A List Of Storms InvitesTool to retrieve a list of storms that you have been invited to.
Get List of Tags in StormTool to retrieve the list of tags that have been created in a Storm.
Get A List Of Your StormsTool to retrieve a list of storms from Stormboard.
Get Authentication InfoTool to retrieve authentication information and API token for the authenticated user.
Get Chat MessagesTool to retrieve a list of chat messages from a Stormboard storm.
Get Idea DataTool to retrieve detailed data and metadata for a specific idea.
Get Info About Your UserTool to retrieve authenticated user profile information.
Get My Storm AccessTool to check if the authenticated user has access to a Storm and retrieve their permission level.
Get Storm TemplateTool to retrieve template data for a Storm including all sections and subsections.
Get Tag Data For An IdeaTool to retrieve tag data for a specific idea in Stormboard.
Get Unread Chat MessagesTool to retrieve unread chat messages from a specific Storm.
Invite Participants to StormTool to invite people to join a Storm by email.
Join a StormTool to join a Storm using its ID and access key.
Mark Chat Messages as ReadTool to mark all chat messages as read in a Storm.
Remove a Favorite StarTool to remove a favorite star from a Storm on the Dashboard.
Reopen a StormTool to reopen a closed Storm.
Update a Line ConnectorTool to update a specific line connector between two ideas.
Update NotificationsTool to update user notification preferences.
Update Section in StormTool to update a section's title, description, and/or character in a Storm.
Update Storm LegendTool to update the color labels of the legend for a storm.
Update Your ProfileTool to update your user profile information.
Verify Your AccountTool to verify a Stormboard account using a verification code.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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

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

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.

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

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

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

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

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

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.

How to build Stormboard MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Stormboard MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Stormboard MCP with Claude Agent SDK

Google ADK

Google ADK

Use Stormboard MCP with Google ADK

LangChain

LangChain

Use Stormboard MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Stormboard MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Stormboard MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Stormboard MCP with LlamaIndex

CrewAI

CrewAI

Use Stormboard MCP with CrewAI

Claude Code

Claude Code

Use Stormboard MCP with Claude Code

Codex

Codex

Use Stormboard MCP with Codex

FAQ

What are the differences in Tool Router MCP and Stormboard MCP?

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.

Can I use Tool Router MCP with Autogen?

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.

Can I manage the permissions and scopes for Stormboard while using Tool Router?

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.

How safe is my data with Composio Tool Router?

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.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free