How to integrate Outlook MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Outlook Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Outlook to AutoGen using the Composio tool router. By the end, you'll have a working Outlook agent that can download latest attachments from my inbox, create new calendar for project deadlines, add rule to move newsletters to folder, get my current automatic reply settings through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Outlook account through Composio's Outlook 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 Outlook
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Outlook tools
  • Run a live chat loop where you ask the agent to perform Outlook 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 Outlook MCP server, and what's possible with it?

The Outlook MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Outlook account. It provides structured and secure access to your email, calendar, and contacts, so your agent can perform actions like sending emails, organizing folders, managing your calendar, and handling attachments on your behalf.

  • Email organization and folder management: Let your agent create, delete, or organize mail folders to keep your inbox tidy and efficient.
  • Calendar and event creation: Easily have your agent set up new calendars, so you can organize meetings and events without lifting a finger.
  • Smart attachments handling: Automatically download files from your emails or add attachments to outgoing messages for seamless file management.
  • Automated rules and filtering: Direct your agent to create email rules that filter, sort, or take action on messages as they arrive.
  • Contact and category organization: Ask your agent to create new contact folders or master categories to streamline how you manage people and projects.

Supported Tools & Triggers

Tools
Triggers
Add mail attachmentTool to add an attachment to an email message.
Create calendarTool to create a new calendar in the signed-in user's mailbox.
Create contact folderTool to create a new contact folder in the user's mailbox.
Create Email RuleCreate email rule filter with conditions and actions
Create mail folderTool to create a new mail folder.
Create master categoryTool to create a new category in the user's master category list.
Delete mail folderDelete a mail folder from the user's mailbox.
Download Outlook attachmentDownloads a specific file attachment from an email message in a microsoft outlook mailbox; the attachment must contain 'contentbytes' (binary data) and not be a link or embedded item.
Get mailbox settingsTool to retrieve mailbox settings.
Get mail deltaTool to retrieve incremental changes (delta) of messages in a mailbox.
Get mail tipsTool to retrieve mail tips such as automatic replies and mailbox full status.
Get master categoriesTool to retrieve the user's master category list.
Get supported languagesTool to retrieve supported languages in the user's mailbox.
Get supported time zonesTool to retrieve supported time zones in the user's mailbox.
List Outlook calendarsTool to list calendars in the signed-in user's mailbox.
List event attachmentsTool to list attachments for a specific outlook calendar event.
List Outlook attachmentsLists metadata (like name, size, and type, but not `contentbytes`) for all attachments of a specified outlook email message.
List event remindersTool to retrieve reminders for events occurring within a specified time range.
Add event attachmentAdds an attachment to a specific outlook calendar event.
Create Calendar EventCreates a new outlook calendar event, ensuring `start datetime` is chronologically before `end datetime`.
Create contactCreates a new contact in a microsoft outlook user's contacts folder.
Create email draftCreates an outlook email draft with subject, body, recipients, and an optional attachment.
Create a draft replyCreates a draft reply in the specified user's outlook mailbox to an existing message (identified by a valid `message id`), optionally including a `comment` and cc/bcc recipients.
Delete ContactPermanently deletes an existing contact, using its `contact id` (obtainable via 'list user contacts' or 'get contact'), from the outlook contacts of the user specified by `user id`.
Delete Calendar EventDeletes an existing calendar event, identified by its unique `event id`, from a specified user's microsoft outlook calendar, with an option to send cancellation notifications to attendees.
Get contactRetrieves a specific outlook contact by its `contact id` from the contacts of a specified `user id` (defaults to 'me' for the authenticated user).
Get contact foldersTool to retrieve a list of contact folders in the signed-in user's mailbox.
Get calendar eventRetrieves the full details of a specific calendar event by its id from a user's outlook calendar, provided the event exists.
Get email messageRetrieves a specific email message by its id from the specified user's outlook mailbox.
Get Outlook profileRetrieves the microsoft outlook profile for a specified user.
Get scheduleRetrieves free/busy schedule information for specified email addresses within a defined time window.
List Outlook contactsRetrieves a user's microsoft outlook contacts, from the default or a specified contact folder.
List eventsRetrieves events from a user's outlook calendar via microsoft graph api, supporting pagination, filtering, property selection, sorting, and timezone specification.
List mail foldersTool to list a user's top-level mail folders.
List MessagesRetrieves a list of email messages from a specified mail folder in an outlook mailbox, with options for filtering (including by conversationid to get all messages in a thread), pagination, and sorting; ensure 'user id' and 'folder' are valid, and all date/time strings are in iso 8601 format.
Move message to folderMove a message to another folder within the specified user's mailbox.
Reply to EmailSends a plain text reply to an outlook email message, identified by `message id`, allowing optional cc and bcc recipients.
Search Outlook messagesSearches messages in a microsoft 365 or enterprise outlook account mailbox, supporting filters for sender, subject, attachments, pagination, and sorting by relevance or date.
Send emailSends an email with subject, body, recipients, and an optional attachment via microsoft graph api; attachments require a non-empty file with valid name and mimetype.
Update calendar eventUpdates specified fields of an existing outlook calendar event.
Update ContactUpdates an existing outlook contact, identified by `contact id` for the specified `user id`, requiring at least one other field to be modified.
Update email messageUpdates specified properties of an existing email message; `message id` must identify a valid message within the specified `user id`'s mailbox.
Update mailbox settingsTool to update mailbox settings for the signed-in user.

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

How to build Outlook MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Outlook MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Outlook MCP with Claude Agent SDK

Google ADK

Google ADK

Use Outlook MCP with Google ADK

LangChain

LangChain

Use Outlook MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Outlook MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Outlook MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Outlook MCP with LlamaIndex

CrewAI

CrewAI

Use Outlook MCP with CrewAI

FAQ

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

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

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

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

Used by agents from

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