How to integrate Toggl Track MCP with OpenAI Agents SDK

This guide walks you through connecting Toggl Track to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Toggl Track agent that can track your time, create clients and projects, manage your tasks, and update time entries through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Toggl Track account through Composio's Toggl Track MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Toggl Track logoToggl Track
Api Key

Toggl Track is a time tracking platform for recording work, organizing projects, and managing workspaces. It helps teams understand where time goes with clear reports, billable hours, and lightweight workflows.

21 Tools

Introduction

This guide walks you through connecting Toggl Track to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Toggl Track agent that can track your time, create clients and projects, manage your tasks, and update time entries through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Toggl Track account through Composio's Toggl Track MCP server.

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

Also integrate Toggl Track with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Toggl Track
  • Configure an AI agent that can use Toggl Track as a tool
  • Run a live chat session where you can ask the agent to perform Toggl Track operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

What is the Toggl Track MCP server, and what's possible with it?

The Toggl Track 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 Track account. It provides structured and secure access to your time entries, workspaces, projects, clients, tasks, and reports, so your agent can track work, manage timers, organize projects, update records, and produce time reports on your behalf.

  • Time entry management: Have your agent create, review, update, or delete time entries, including their descriptions, timing, billable status, tags, and work assignments.
  • Running timer control: Let the agent check your current timer, start a new running time entry, or stop work in progress.
  • Workspace and project organization: Direct your agent to list workspaces and manage projects, clients, and tasks used to organize tracked work.
  • Detailed time reporting: Instruct your agent to produce detailed time reports for a workspace and date range, grouped into useful report rows.
  • Bulk record updates: Have your agent apply the same description or billable status to multiple time entries at once.

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:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Toggl Track project
  • Some knowledge of Python or Typescript
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
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Toggl Track.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Toggl Track
const session = await composio.create(userId as string, {
  toolkits: ['toggl_track'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only toggl_track.
  • The router checks the user's Toggl Track connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Toggl Track.
  • This approach keeps things lightweight and lets the agent request Toggl Track tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Toggl Track. Help users perform Toggl Track operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Toggl Track and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a hostedMcpTool that connects to the MCP server URL we created earlier.
  • The headers object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Toggl Track operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

// Simple CLI
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: 'You: ',
});

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

  if (!text) {
    rl.prompt();
    return;
  }

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Toggl Track.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Toggl Track and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['toggl_track'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Toggl Track. Help users perform Toggl Track operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

  // Simple CLI
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: ',
  });

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

    if (!text) {
      rl.prompt();
      return;
    }

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

main().catch((err) => {
  console.error('Fatal error:', err);
  process.exit(1);
});

Conclusion

This was a starter code for integrating Toggl Track MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Toggl Track.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

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

Bulk Update Time Entries

Apply the same description and/or billable state to 1 to 100 Toggl Track time entries in one provider-native request.

Create Client

Create a client in a workspace for grouping projects.

Create Project

Create a project in a workspace for organizing time entries and tasks.

Create Task

Create a task under an active project for more specific time-entry assignment.

Create Time Entry

Create a running or completed time entry in a workspace; omit duration and stop to start a running timer.

Delete Client

Permanently delete one client from a Toggl Track workspace.

Delete Project

Delete one project while preserving its time entries by unassigning them from the project.

Delete Task

Permanently delete one task from its parent project.

Delete Time Entry

Permanently delete one time entry from a workspace.

Get Current Time Entry

Return the currently running time entry for the connected user, or indicate that no timer is running.

Get Current User

Return the connected Toggl Track user's identity and defaults, including the default workspace ID, without exposing credentials.

Get Time Entry

Get one time entry by ID, with optional related-entity and sharing metadata.

List Time Entries

List the connected user's time entries in an explicit date range, optionally including related project, task, user, and sharing metadata.

List Workspace Resources

Find projects, clients, tags, or tasks in a workspace and return their IDs for time-entry and resource-management tools.

List Workspaces

List workspaces accessible to the connected user and return the IDs needed by workspace-scoped tools, without exposing private tokens or calendar URLs.

Run Detailed Time Report

Return one page of detailed, grouped time-entry report rows for a workspace and date range, with an opaque cursor for the next page.

Stop Time Entry

Stop a currently running time entry and return its finalized timing data.

Update Client

Update a client's name, notes, or external reference.

Update Project

Update a project's name, client, active state, privacy, color, or date range.

Update Task

Update a task's name, completion state, estimate, assignee, or external reference.

Update Time Entry

Update the timing, description, assignment, billable state, or tags of an existing time entry.

FAQ

Frequently asked questions

With a standalone Toggl Track MCP server, the agents and LLMs can only access a fixed set of Toggl Track tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Toggl Track and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. OpenAI Agents SDK 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 Track tools.

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

Start with Toggl Track.It takes 30 seconds.

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

Start building