Taskdog

v1.0.0Developer Toolsstable

Local-first task management with CLI, TUI, and REST API. MCP server enables Claude to manage tasks, track time, optimize schedules, and handle dependencies.

claude-codecliclickfastapimakefile
Share:
254
Stars
0
Downloads
0
Weekly
0/5

What is Taskdog?

Taskdog is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to local-first task management with cli, tui, and rest api. mcp server enables claude to manage tasks, track time, optimize schedules, and handle dependencies.

Local-first task management with CLI, TUI, and REST API. MCP server enables Claude to manage tasks, track time, optimize schedules, and handle dependencies.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Local-first task management with CLI, TUI, and REST API. MCP

Use Cases

Manage tasks locally using CLI, TUI, or REST API.
Track time and optimize schedules through Claude.
Handle task dependencies and automation workflows.
Kohei-Wada

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx taskdog

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Taskdog

Taskdog is a local-first task management system that exposes a full MCP server (taskdog-mcp) for Claude Desktop, allowing Claude to create, update, and organize tasks without leaving your conversation. It connects to a locally running taskdog-server over a REST API, and supports rich operations including task dependencies, time tracking with planned-vs-actual comparison, 9 schedule optimization algorithms, and Gantt chart visualization. Developers and project managers who want AI-assisted task planning and dependency management without a cloud SaaS subscription will find it especially useful.

Prerequisites

  • Python 3.12 or higher installed
  • uv package manager installed (https://github.com/astral-sh/uv)
  • taskdog-server running locally (default: http://127.0.0.1:8000)
  • Claude Desktop or another MCP-compatible client
  • Linux or macOS (Windows supported via WSL2)
1

Clone and install Taskdog

Clone the repository and run the automated installer which sets up the CLI, TUI, REST server, and a systemd/launchd background service.

git clone https://github.com/Kohei-Wada/taskdog.git
cd taskdog
make install
2

Verify the server is running

After installation the background service should start automatically. Confirm the REST API is reachable at its default address.

curl http://127.0.0.1:8000/health
3

Install the taskdog-mcp package

Install the MCP bridge package from PyPI so that the `taskdog-mcp` command is available on your PATH.

pip install taskdog-mcp
4

Add the MCP server to your Claude Desktop config

Open your Claude Desktop configuration file and add the taskdog MCP server entry. On macOS the file is at ~/Library/Application Support/Claude/claude_desktop_config.json.

{
  "mcpServers": {
    "taskdog": {
      "command": "taskdog-mcp"
    }
  }
}
5

Optionally configure environment variables

If you changed the server host, port, or set an API key, pass those values via environment variables in the config.

{
  "mcpServers": {
    "taskdog": {
      "command": "taskdog-mcp",
      "env": {
        "TASKDOG_API_HOST": "127.0.0.1",
        "TASKDOG_API_PORT": "8000",
        "TASKDOG_API_KEY": "your-api-key"
      }
    }
  }
}
6

Restart Claude Desktop and test

Restart Claude Desktop so the new MCP server entry is picked up. You should now be able to ask Claude to list or create tasks directly.

Taskdog Examples

Client configuration

Minimal Claude Desktop configuration for taskdog-mcp after installing via pip.

{
  "mcpServers": {
    "taskdog": {
      "command": "taskdog-mcp",
      "env": {
        "TASKDOG_API_HOST": "127.0.0.1",
        "TASKDOG_API_PORT": "8000"
      }
    }
  }
}

Prompts to try

Example prompts that exercise the task management, dependency, and analytics tools exposed by taskdog-mcp.

- "List all my open tasks and show which ones are executable right now."
- "Create a task called 'Write unit tests' with priority 8 and add it as a dependency of 'Refactor auth module'."
- "Show me statistics on how many tasks I completed this week vs. last week."
- "Decompose the task 'Launch v2.0' into subtasks and set dependencies between them."
- "Start the task 'Fix login bug' and update its notes with the current stack trace."

Troubleshooting Taskdog

Claude says the taskdog MCP server is not connected or tools are unavailable.

Ensure `taskdog-server` is running on the expected host and port before starting Claude Desktop. Run `curl http://127.0.0.1:8000/health` to verify. Also confirm `taskdog-mcp` is on your PATH with `which taskdog-mcp`.

Permission denied or command not found when running taskdog-mcp.

Make sure the pip install target is on your system PATH. If you used a virtual environment, either activate it or provide the full path to the binary in the `command` field of the MCP config.

Taskdog server does not start automatically after installation.

On Linux, run `systemctl --user enable --now taskdog` to enable the systemd service. On macOS, check the launchd plist installed under `~/Library/LaunchAgents/` and run `launchctl load` on it.

Frequently Asked Questions about Taskdog

What is Taskdog?

Taskdog is a Model Context Protocol (MCP) server that local-first task management with cli, tui, and rest api. mcp server enables claude to manage tasks, track time, optimize schedules, and handle dependencies. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Taskdog?

Follow the installation instructions on the Taskdog GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Taskdog?

Taskdog works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Taskdog free to use?

Yes, Taskdog is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "taskdog": { "command": "npx", "args": ["-y", "taskdog"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Taskdog?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides