How to integrate Roam MCP with Autogen

This guide walks you through connecting Roam to AutoGen using the Composio tool router. By the end, you'll have a working Roam agent that can summarize unread roam team messages, send secure file to compliance channel, find recent chats about incident response through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Roam account through Composio's Roam MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Roam logoRoam
Api KeyOauth2

Roam HQ is a secure messaging, chat, file sharing, and collaboration platform. It helps teams communicate with enterprise-grade security and compliance controls.

39 Tools

Introduction

This guide walks you through connecting Roam to AutoGen using the Composio tool router. By the end, you'll have a working Roam agent that can summarize unread roam team messages, send secure file to compliance channel, find recent chats about incident response through natural language commands.

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

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

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

The Roam MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Roam account. It provides structured and secure access to your chats, messages, shared files, meeting links, and directory information, so your agent can post to chats, message groups, upload files, retrieve meeting links, and look up chat participants on your behalf.

  • Chat messaging: Have your agent post updates, announcements, or replies directly to a Roam chat.
  • Group communication: Direct your agent to send a message to selected recipients for team coordination and follow-ups.
  • File sharing: Let the agent upload a file to Roam so it can be shared as a chat attachment.
  • Meeting access: Instruct your agent to retrieve a Roam meeting link when you need to join or share a conversation.
  • Directory and schema lookup: Have your agent look up information about chat participants or retrieve a specific SCIM schema definition.

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

Supported Tools

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

Add group members

Add one or more group members and/or admins to an existing Roam group.

Add Reaction to Message

Add an emoji reaction to a message in a chat.

Create Group

Create a group address that can be used for chat.

Create Roam SCIM Group

Tool to create a new group in your Roam organization using SCIM 2.

Create Roam User

Create a new user in Roam via SCIM 2.

Delete Roam Group

Archive a group in Roam using SCIM 2.

Delete Roam User

Archive a user in Roam using SCIM 2.

Get Address Info

Get information about a chat address, which is the name for any entity that may participate in a chat, such as a user, visitor, or bot.

Get chat history

Lists messages in a chat, filtered by date range (after/before).

Get meeting link

Tool to get a meeting link.

Get Roam SCIM Resource Types

Returns the list of SCIM 2.

Get SCIM service provider config

Tool to retrieve Roam's SCIM service provider configuration.

Get SCIM schema

Retrieves the definition of a specific SCIM 2.

Get user by ID (SCIM)

Tool to retrieve a single user by their Roam Person ID using SCIM 2.

Test API Connectivity

Test endpoint for API connectivity.

Get token info

Retrieves information about the current Roam access token.

Get user info

Get detailed information about a single user in your Roam workspace.

List Roam Chats

Lists all accessible chats, which consist of all DMs, MultiDMs, and Channels that your bot has been added to, in addition to all public channels.

List group members

List members in a group in your Roam workspace.

List SCIM Groups

Returns a paginated list of groups in your Roam organization via SCIM 2.

List Roam Lobbies

Lists active lobbies in your Roam account.

List Roam Meetings

Lists all meetings in your home Roam, filtered by date range.

List Roam Recordings

Tool to list all recordings in your home Roam.

List users (SCIM)

Tool to list users in your Roam organization using SCIM 2.

List SCIM Schemas

Tool to list all SCIM 2.

List Roam Transcripts

Lists all transcripts in your Roam workspace, filtered by date range.

List User Audit Log

Tool to get a list of user audit log entries for the account.

List Users

Tool to list all users in the Roam workspace.

Lookup user by email

Look up a user in your Roam workspace by their email address.

Patch a group

Partially updates a group using SCIM 2.

Patch user (SCIM)

Partially updates a user using SCIM 2.

Post message to chat

Post a message to a chat.

Remove group members

Tool to remove one or more members from a group in your Roam workspace.

Replace Roam SCIM Group

Fully replaces a group's attributes using SCIM 2.

Replace Roam User

Fully replaces (updates) a user's attributes in Roam via SCIM 2.

Send message to group

Sends the given message to the specified recipients.

Send Typing Indicator

Tool to notify other chat participants that you are typing.

Update a meeting link

Update settings for an existing meeting link in Roam.

Upload File to Roam

Upload a file to Roam so it can be sent as a chat attachment.

FAQ

Frequently asked questions

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

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

Start with Roam.It takes 30 seconds.

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

Start building