mcpField
T
TimeTagger MCP Server

TimeTagger MCP Server

Local
github.com/regismesquitaProductivity3Updated 82w ago
Repository

About TimeTagger MCP Server

TimeTagger MCP Server connects TimeTagger with Claude and other MCP-compatible assistants. It provides tools and resources for managing time records, timers, tags, and settings.

Key features

  1. 01Query records by time range
  2. 02Create, update, and hide records
  3. 03Start and stop timers
  4. 04Summarize time by tags
  5. 05Read and update settings

Use cases

  1. 01Review records from a selected period
  2. 02Track work with start and stop timers
  3. 03Summarize time spent on tagged activities

MCP support

The MCP server exposes TimeTagger record, timer, tag-summary, and settings operations as tools, plus configuration, record, settings, and update resources.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "timetagger": {
      "command": "uvx",
      "args": [
        "git+https://github.com/regismesquita/timetagger-mcp"
      ],
      "env": {
        "TIMETAGGER_API_KEY": "<TIMETAGGER_API_KEY>",
        "TIMETAGGER_API_URL": "<TIMETAGGER_API_URL>"
      }
    }
  }
}
Run commanduvx 'git+https://github.com/regismesquita/timetagger-mcp'
Environment variables to set
TIMETAGGER_API_KEYSecret
TIMETAGGER_API_URL

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypigit+https://github.com/regismesquita/timetagger-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

TimeTagger MCP Server

This is a Model Context Protocol (MCP) server for interacting with TimeTagger. It provides tools to query and manage your time records through Claude or other MCP-compatible AI assistants.

Features

  • Query time records within specific timeframes
  • Create new time records
  • Update existing records
  • Hide/delete records
  • Get time summaries by tags
  • Start and stop timers
  • Manage TimeTagger settings

Claude Desktop Installation

Add this to your claude_desktop_config.json:

"timetagger": {
  "command": "uvx",
  "args": [
    "--from",
    "git+https://github.com/regismesquita/timetagger-mcp",
    "timetagger-mcp"
  ],
  "env": {
    "TIMETAGGER_API_KEY": "your-api-key-here",
    "TIMETAGGER_API_URL": "https://your-timetagger-instance.com/api/v2"
  }
}

Manual Installation

  1. Ensure you have uv installed:

    brew install uv

  2. Install the required dependencies:

    uv pip install -r requirements.txt

Configuration

The server requires your TimeTagger API key to be set as an environment variable:

export TIMETAGGER_API_KEY="your-api-key-here"
export TIMETAGGER_API_URL="https://your-timetagger-instance.com/api/v2"

Usage

Running in Development Mode

For testing and development, use:

fastmcp dev timetagger_mcp.py

This will launch the MCP Inspector interface where you can test the tools and resources.

Installing for Claude Desktop

To use with Claude Desktop:

fastmcp install timetagger_mcp.py

Available Tools

  • get_records(start_time, end_time): Get records within a time range
  • get_recent_records(hours): Get records from the last N hours
  • get_today_records(): Get today's records
  • create_record(description, start_time, end_time): Create a new record
  • update_record(key, description, start_time, end_time): Update an existing record
  • hide_record(key): Hide/delete a record
  • start_timer(description): Start a new timer
  • stop_timer(key): Stop an ongoing timer
  • find_records_by_tag(tag, days): Find records with a specific tag
  • get_time_summary(days): Get a summary of time spent on different tags
  • get_settings(): Get all TimeTagger settings
  • update_setting(key, value): Update a TimeTagger setting

Available Resources

  • timetagger://config: Get the TimeTagger configuration
  • timetagger://records/{timerange}: Get records within a timerange
  • timetagger://settings: Get all settings
  • timetagger://updates/{since}: Get updates since a specific timestamp

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.