How to integrate Google Calendar MCP with Autogen

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

Introduction

This guide walks you through connecting Google Calendar to AutoGen using the Composio tool router. By the end, you'll have a working Google Calendar agent that can create a meeting with the marketing team, list all events scheduled for next week, delete tomorrow’s canceled event from my calendar, update the time for friday’s project sync through natural language commands.

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

The Google Calendar MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Google Calendar account. It provides structured and secure access to your calendars and events, so your agent can schedule meetings, create or modify events, list upcoming appointments, and manage calendars—all on your behalf.

  • Automated event creation and scheduling: Easily instruct your agent to add new events, meetings, or reminders with specific times, attendees, and details.
  • Event listing and agenda overview: Have your agent list all upcoming, past, or filtered events on any of your calendars to keep you on top of your schedule.
  • Calendar management and customization: Direct your agent to create new calendars, update calendar details, or even insert calendars into your list for better organization.
  • Event updating and deletion: Let your agent modify existing events or remove events that are no longer needed, keeping your calendar up to date.
  • Complete calendar clearing: Ask your agent to clear all events from a primary calendar or delete secondary calendars entirely when you need a fresh start.

Supported Tools & Triggers

Tools
Triggers
Insert Calendar into ListInserts an existing calendar into the user's calendar list.
Update Calendar List EntryUpdates an existing entry on the user\'s calendar list.
Delete CalendarDeletes a secondary calendar.
Update CalendarUpdates metadata for a calendar.
Clear CalendarClears a primary calendar.
Create EventCreates an event on a google calendar, needing rfc3339 utc start/end times (end after start) and write access to the calendar.
Delete eventDeletes a specified event by `event id` from a google calendar (`calendar id`); this action is idempotent and raises a 404 error if the event is not found.
Create a calendarCreates a new, empty google calendar with the specified title (summary).
Get Event InstancesReturns instances of the specified recurring event.
List EventsReturns events on the specified calendar.
Move EventMoves an event to another calendar, i.
Watch EventsWatch for changes to events resources.
Find eventFinds events in a specified google calendar using text query, time ranges (event start/end, last modification), and event types; ensure `timemin` is not chronologically after `timemax` if both are provided.
Find free slotsFinds free/busy time slots in google calendars for specified calendars within a defined time range (defaults to the current day utc if `time min`/`time max` are omitted), enhancing busy intervals with event details; `time min` must precede `time max` if both are provided.
Query Free/Busy InformationReturns free/busy information for a set of calendars.
Get Google CalendarRetrieves a specific google calendar, identified by `calendar id`, to which the authenticated user has access.
Get current date and timeGets the current date and time, allowing for a specific timezone offset.
List ACL RulesRetrieves the list of access control rules (acls) for a specified calendar, providing the necessary 'rule id' values required for updating specific acl rules.
List Google CalendarsRetrieves calendars from the user's google calendar list, with options for pagination and filtering.
Patch CalendarPartially updates (patches) an existing google calendar, modifying only the fields provided; `summary` is mandatory and cannot be an empty string, and an empty string for `description` or `location` clears them.
Patch EventUpdates specified fields of an existing event in a google calendar using patch semantics (array fields like `attendees` are fully replaced if provided); ensure the `calendar id` and `event id` are valid and the user has write access to the calendar.
Quick Add EventParses natural language text to quickly create a basic google calendar event with its title, date, and time, suitable for simple scheduling; does not support direct attendee addition or recurring events, and `calendar id` must be valid if not 'primary'.
Remove attendee from eventRemoves an attendee from a specified event in a google calendar; the calendar and event must exist.
List SettingsReturns all user settings for the authenticated user.
Watch SettingsWatch for changes to settings resources.
Sync EventsSynchronizes google calendar events, performing a full sync if no `sync token` is provided or if a 410 gone error (due to an expired token) necessitates it, otherwise performs an incremental sync for events changed since the `sync token` was issued.
Update ACL RuleUpdates an access control rule for the specified calendar.
Update Google eventUpdates an existing event by `event id` in a google calendar; this is a full put replacement, so provide all desired fields as unspecified ones may be cleared or reset.

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 Google Calendar 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 Google Calendar 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 Google Calendar 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 Google Calendar session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["googlecalendar"]
    )
    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 Google Calendar 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 Google Calendar assistant agent with MCP tools
    agent = AssistantAgent(
        name="googlecalendar_assistant",
        description="An AI assistant that helps with Google Calendar 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 Google Calendar 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 Google Calendar 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 Google Calendar 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 Google Calendar and AutoGen:

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

How to build Google Calendar MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Google Calendar MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Google Calendar MCP with Claude Agent SDK

Google ADK

Google ADK

Use Google Calendar MCP with Google ADK

LangChain

LangChain

Use Google Calendar MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Google Calendar MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Google Calendar MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Google Calendar MCP with LlamaIndex

CrewAI

CrewAI

Use Google Calendar MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Google Calendar MCP?

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

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

Yes, absolutely. You can configure which Google Calendar 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 Google Calendar 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