Streamline your Toggl time tracking by automating the start and stop of tasks directly through an MCP server. Effortlessly manage your time entries and retrieve workspace information.

Outcomes

What it gets done

Start and stop time tracking for tasks

Retrieve current time entry details

List available Toggl workspaces

Integrate Toggl Track API v9

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-lazy-toggl-mcp | bash

Capabilities

Tools your agent gets

start_tracking

Start time tracking for a new task with optional workspace, project, and tags

stop_tracking

Stop the current time entry

list_workspaces

Show all available workspaces with their IDs and names

show_current_time_entry

Show the current time entry with details: description, workspace, duration, and tags

Overview

Lazy Toggl MCP Server

Lazy Toggl MCP Server gives an AI assistant minimal start/stop/status control over Toggl Track time entries and workspace listing. Use it for quick, conversational Toggl time tracking; it doesn't cover editing past entries, reports, or project management.

What it does

Lazy Toggl MCP Server gives an AI assistant simple control over Toggl Track time tracking: starting a new tracked task, stopping the currently running entry, checking what's currently being tracked, and listing available workspaces. It talks directly to the Toggl Track API v9 (/me, /workspaces, /me/time_entries/current, and the time-entry create/stop endpoints).

When to use - and when NOT to

Use this connector when you want an assistant to start or stop a Toggl time entry, check what task is currently being tracked (and for how long), or list your Toggl workspaces - a lightweight way to manage time tracking conversationally.

Do not use it for more advanced Toggl operations like editing past entries, generating reports, or managing projects/tags beyond what's passed at tracking start - the tool set is intentionally minimal ("lazy") and scoped to start/stop/status/workspace listing.

Inputs and outputs

start_tracking takes a task title plus optional workspace ID, project ID, and tags. stop_tracking and list_workspaces take no input. show_current_time_entry takes no input and returns either the running entry's details (description, ID, workspace, start time, duration, tags, project) or a message that nothing is running.

Capabilities

start_tracking: start tracking time for a new task, with optional workspace, project, and tags
stop_tracking: stop the currently running time entry
list_workspaces: list all available Toggl workspaces with IDs and names
show_current_time_entry: show the currently running entry's details, or indicate nothing is running

Under the hood these four tools map directly onto five Toggl Track API v9 endpoints: GET /me for user info, GET /workspaces for the workspace list, GET /me/time_entries/current for the running entry, POST /workspaces/{workspace_id}/time_entries to start tracking, and PATCH /workspaces/{workspace_id}/time_entries/{time_entry_id}/stop to stop it.

How to install

cd lazy-toggl-mcp
uv sync

Get your Toggl API token by signing into Toggl Track, opening your profile picture/avatar menu in the top right, going to Profile or Settings, and copying the API Token string. Then configure your MCP client, replacing the directory path and token placeholders with real values:

{
  "mcpServers": {
    "lazy-toggl-mcp": {
      "autoApprove": [],
      "disabled": false,
      "timeout": 60,
      "type": "stdio",
      "transportType": "stdio",
      "command": "uv",
      "args": ["run", "--directory", "/path/to/lazy-toggl-mcp", "python", "server.py"],
      "env": { "TOGGL_API_TOKEN": "your-actual-api-token-here" }
    }
  }
}

The project ships as a small Python package (src/toggl_server/ with main.py, models.py, toggl_api.py, and utils.py), plus a top-level server.py MCP entry point, a separate main.py CLI for testing outside an MCP client, and uv-managed pyproject.toml/uv.lock dependency files. It's released under the MIT License, described in the source as free to modify and use as needed.

Who it's for

Toggl Track users who want a minimal, conversational way to start/stop time tracking and check their current entry without switching apps.

Source README

Lazy Toggl MCP Server

A Model Context Protocol (MCP) server that provides tools for interacting with Toggl time tracking.

Features

Start/stop time tracking
Get current entry
List workspaces

API

Tools

start_tracking
- Start tracking time for a new task
- Inputs:
  - title (string): Title/description of the task to track
  - workspace_id (integer): Workspace ID (optional, uses default if not provided)
  - project_id (integer): Project ID (optional)
  - tags (string[]): List of tags (optional)
stop_tracking
- Stop the currently running time entry
- No input required
- Returns confirmation of stopped time entry
list_workspaces
- List all available workspaces
- No input required
- Returns list of workspaces with their IDs and names
show_current_time_entry
- Show the currently running time entry, if any
- No input required
- Returns:
  - If tracking: Task description, entry ID, workspace, start time, running duration, tags, and project (if any)
  - If not tracking: A message indicating no time entry is currently running

Integration with Toggl Track API

This server uses the Toggl Track API v9. The following endpoints are utilized:

GET /me - Get user information
GET /workspaces - List workspaces
GET /me/time_entries/current - Get current running time entry
POST /workspaces/{workspace_id}/time_entries - Start time tracking
PATCH /workspaces/{workspace_id}/time_entries/{time_entry_id}/stop - Stop time tracking

Installation

Clone/create this project
Install dependencies with uv:
```
cd lazy-toggl-mcp
uv sync
```

Configuration

Get Your Toggl API Token

Go to Toggl Track
Sign in to your account
Click on your profile picture/avatar in the top right corner
Go to "Profile" or "Settings"
Find your "API Token" - copy this long string of characters

Configure MCP Server

Add the following configuration to your MCP settings file:

{
  "mcpServers": {
    "lazy-toggl-mcp": {
      "autoApprove": [],
      "disabled": false,
      "timeout": 60,
      "type": "stdio",
      "transportType": "stdio",
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/lazy-toggl-mcp",
        "python",
        "server.py"
      ],
      "env": {
        "TOGGL_API_TOKEN": "your-actual-api-token-here"
      }
    }
  }
}

Important: Replace /path/to/lazy-toggl-mcp with the actual path to this project and your-actual-api-token-here with your real Toggl API token.

Project Structure

lazy-toggl-mcp/
├── src/
│   └── toggl_server/
│       ├── __init__.py      # Package initialization
│       ├── main.py          # MCP server implementation (new structure)
│       ├── models.py        # Data models and type definitions
│       ├── toggl_api.py     # Toggl API client
│       └── utils.py         # Utility functions
├── main.py                  # CLI interface for testing
├── server.py                # Main MCP server entry point
├── pyproject.toml           # Project configuration and dependencies
├── README.md                # This file
├── uv.lock                  # Dependency lock file
├── .gitignore               # Git ignore patterns
└── .python-version          # Python version specification

Discussion

Automate Toggl Time Tracking

What it gets done

Add it to your toolbox

Tools your agent gets

Lazy Toggl MCP Server

What it does

When to use - and when NOT to

Inputs and outputs

Capabilities

How to install

Who it's for

Lazy Toggl MCP Server

Features

API

Tools

Integration with Toggl Track API

Installation

Configuration

Get Your Toggl API Token

Configure MCP Server

Project Structure

Questions & comments · 0