How to integrate Toggl MCP with Pydantic AI

This guide walks you through connecting Toggl to Pydantic AI 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 your workspace, get details of your current running timer through natural language commands. This guide will help you understand how to give your Pydantic AI 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.

Get started for freeGet a demo
Toggl logoToggl
Api Key

Toggl is a time tracking platform for managing work hours and productivity. It helps individuals and teams monitor tasks, analyze time usage, and optimize workflows.

56 Tools

Introduction

This guide walks you through connecting Toggl to Pydantic AI 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 your workspace, get details of your current running timer through natural language commands.

This guide will help you understand how to give your Pydantic AI 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.

Also integrate Toggl with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Toggl
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Toggl workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

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.

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 step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
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 pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Toggl
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Toggl
  • MCPServerStreamableHTTP connects to the Toggl MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Toggl
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["toggl"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Toggl tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
toggl_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[toggl_mcp],
    instructions=(
        "You are a Toggl assistant. Use Toggl tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Toggl endpoint
  • The agent uses GPT-5 to interpret user commands and perform Toggl operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Toggl.\n")

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", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Toggl API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Toggl and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Toggl
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["toggl"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    toggl_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[toggl_mcp],
        instructions=(
            "You are a Toggl assistant. Use Toggl tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Toggl.\n")

    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", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Toggl through Composio's Tool Router. With this setup, your agent can perform real Toggl actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Toggl for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

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

Create Client

Tool to create a new client in a workspace.

Create Group

Tool to create a new group in a Toggl organization.

Create Invitation

Tool to send invitations to join a Toggl organization.

Create Organization

Tool to create a new organization with a default workspace in Toggl Track.

Create Project

Creates a new project in a Toggl workspace.

Create Tag

Tool to create a new tag in a workspace.

Create Time Entry

Tool to create a new time entry in the specified workspace.

Add User to Workspace Project

Tool to add a user to workspace project users.

Delete Toggl Client

Tool to delete a client in Toggl.

Delete Group

Tool to delete a group from a Toggl organization.

Delete Project Group

Tool to delete a project group from a Toggl workspace.

Delete Subscription

Tool to delete a webhook subscription in Toggl.

Delete Tag

Deletes a tag from a Toggl workspace.

Disable Weekly Report

Tool to disable weekly report email notifications.

Bulk Edit Time Entries

Tool to bulk edit multiple time entries in a workspace using JSON Patch operations.

Get All Plans

Tool to retrieve all available Toggl subscription plans and their features.

Get Client Details

Retrieves detailed information about a specific client in Toggl Track by its client ID and workspace ID.

Get Countries

Tool to retrieve all countries supported by Toggl.

Get Country Subdivisions

Tool to retrieve all subdivisions (states, provinces, regions) for a specific country in Toggl Track.

Get Currencies

Tool to retrieve the list of all currencies supported by Toggl Track.

Get Current Time Entry

Retrieves the currently running time entry for the authenticated user.

Get Event Filters

Retrieve the list of supported event filters for Toggl webhooks.

Get JWKS Keys

Retrieves the current JWKS (JSON Web Key Set) keyset used to sign JWT tokens.

List Clients

Retrieve a list of clients from a Toggl Track workspace with optional filtering by status and name.

Get My Location

Retrieves the authenticated user's last known location information including city, state, country, and coordinates.

Get My Quota

Tool to retrieve API rate limit quota for the authenticated user.

Get Organization Details

Retrieves detailed information about a specific Toggl organization including subscription plan, trial status, user count, and workspace settings.

Get Organization Groups

Retrieves all groups within a Toggl organization, including group members and workspace assignments.

Get Organization Users

Retrieves a list of users belonging to a Toggl organization.

Get Project Details

Tool to retrieve details of a specific project.

Get Projects

Tool to retrieve a list of projects from a Toggl workspace.

Get Public Subscription Plans

Tool to retrieve all publicly available subscription plans from Toggl.

Get Webhooks Status

Tool to retrieve the Toggl Webhooks server status.

Get Tags

Retrieve all tags in a Toggl workspace.

List Tasks

Tool to list tasks in a workspace or within a specific project.

Get Time Entries

Retrieve time entries for the authenticated user with flexible filtering options.

Get Time Entry

Tool to retrieve a specific time entry by its ID.

Get Timezone Offsets

Tool to retrieve all available timezone offsets from Toggl.

Get Timezones

Tool to retrieve all available timezones supported by Toggl Track.

Get User Clients

Retrieves all clients accessible to the authenticated user across all their workspaces.

Get User Preferences

Retrieves the authenticated user's preferences including timezone, date/time formats, notification settings, and enabled alpha/experimental features.

Get User Projects

Tool to retrieve all projects for the authenticated user.

Get User Tags

Tool to retrieve tags associated with the current user.

Get User Tasks

Retrieve all tasks across all workspaces accessible to the authenticated user.

Get User Workspaces

Tool to retrieve all workspaces the authenticated user belongs to.

Get Workspace Details

Retrieves comprehensive details and settings for a specific Toggl workspace by ID.

Get Workspace Logo

Tool to get workspace logo.

Get Workspace Preferences

Retrieves workspace preferences including the initial pricing plan and whether start/end times are hidden.

Get Workspace Users

Retrieves all users who belong to a specific Toggl workspace.

Stop Time Entry

Tool to stop a running time entry in a workspace.

Disable Product Emails

Tool to disable product emails for the authenticated user using a disable code.

Update Tag

Tool to update an existing tag in a specified workspace.

Send Demo Email

Tool to send a demo request email through Toggl's system.

Send Email to Contact

Tool to send an email to a contact via Toggl's smail service.

Send Smail Meet

Tool to send an email for meet.

Update Client

Updates an existing client in a Toggl workspace.

FRAMEWORKS

How to build Toggl MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Toggl MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Toggl MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Toggl MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Toggl MCP with Claude Cowork

Codex logo

Codex

Use Toggl MCP with Codex

OpenClaw logo

OpenClaw

Use Toggl MCP with OpenClaw

Hermes logo

Hermes

Use Toggl MCP with Hermes

CLI logo

CLI

Use Toggl MCP with CLI

Google ADK logo

Google ADK

Use Toggl MCP with Google ADK

LangChain logo

LangChain

Use Toggl MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Toggl MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Toggl MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Toggl MCP with LlamaIndex

CrewAI logo

CrewAI

Use Toggl MCP with CrewAI

FAQ

Frequently asked questions

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.

Yes, you can. Pydantic AI 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.

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.

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.

Start with Toggl.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies