How to integrate Toggl MCP with Autogen

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

Introduction

This guide walks you through connecting Toggl to AutoGen using the Composio tool router. By the end, you'll have a working Toggl agent that can start a new time entry for coding, list all clients in my workspace, get details of my current running timer, create a new project for marketing through natural language commands.

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

The Toggl MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Toggl account. It provides structured and secure access to your time tracking data, so your agent can perform actions like logging time entries, managing clients and projects, handling tags, and retrieving detailed activity reports on your behalf.

  • Automated time entry management: Let your agent start, stop, and create new time entries with precise details, making it easy to track your work hours hands-free.
  • Client and project organization: Easily add new clients or projects, fetch client details, or remove outdated clients to keep your workspace up to date and well-structured.
  • Real-time activity tracking: Ask your agent to retrieve the currently running time entry or list recent activities, so you always know where your time is going.
  • Tag management and organization: Automatically create or delete tags to categorize your time entries, helping you analyze how your time is spent across different tasks.
  • Comprehensive workspace administration: Have your agent create organizations, set up workspaces, and ensure all your time tracking infrastructure is ready to go without manual setup.

Supported Tools & Triggers

Tools
Create ClientTool to create a new client in a workspace.
Create OrganizationTool to create a new organization with a default workspace.
Create ProjectTool to create a new project in a workspace.
Create TagTool to create a new tag in a workspace.
Create Time EntryTool to create a new time entry in the specified workspace.
Delete Toggl ClientTool to delete a client in toggl.
Delete TagTool to delete a tag from a workspace.
Get Client DetailsTool to retrieve details of a specific client.
Get Current Time EntryTool to retrieve the current running time entry for the authenticated user.
List ClientsTool to retrieve a list of clients from a toggl workspace.
Get Organization DetailsTool to retrieve details of a specific organization by its id.
Get Organization GroupsTool to retrieve list of groups in a specified organization.
Get Organization UsersTool to retrieve all users in a toggl organization by organization id.
Get Project DetailsTool to retrieve details of a specific project.
Get ProjectsTool to retrieve a list of projects from a toggl workspace.
Get TagsTool to retrieve all tags in a toggl workspace.
List TasksTool to list tasks in a workspace or within a specific project.
Get Time EntriesTool to list the latest time entries for the authenticated user.
Get Time EntryTool to retrieve a specific time entry by its id.
Get User ClientsTool to fetch the list of clients accessible by the authenticated user.
Get User PreferencesTool to retrieve current user's preferences and alpha features.
Get User ProjectsTool to retrieve all projects for the authenticated user.
Get User TagsTool to retrieve tags associated with the current user.
Get User TasksTool to retrieve tasks from projects in which the authenticated user is participating.
Get User WorkspacesTool to retrieve all workspaces the authenticated user belongs to.
Get Workspace DetailsTool to retrieve details of a specific workspace.
Get Workspace PreferencesTool to retrieve workspace preferences.
Get Workspace UsersTool to retrieve all users in a toggl workspace by workspace id.
Stop Time EntryTool to stop a running time entry in a workspace.
Update TagTool to update an existing tag in a specified workspace.
Update ClientTool to update details of a specific client.

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

How to build Toggl MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Toggl MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Toggl MCP with Claude Agent SDK

Google ADK

Google ADK

Use Toggl MCP with Google ADK

LangChain

LangChain

Use Toggl MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Toggl MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Toggl MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Toggl MCP with LlamaIndex

CrewAI

CrewAI

Use Toggl MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Toggl 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 Toggl 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