Gotask

Provides a local MCP server to list and run Taskfile tasks from a client within the current project context.

python

3

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "paddyalton-gotask-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp",
        "--directory",
        "/path/to/gotask-mcp",
        "mcp",
        "run",
        "/path/to/gotask-mcp/src/server.py"
      ]
    }
  }
}

You run a dedicated MCP server that lets you discover and execute Taskfile-based tasks from a client. It operates in an isolated environment and shares contextual project information with the client, enabling automated task execution and QA checks within your development workflow.

How to use

To use this MCP server with a client, start the local MCP server instance and then connect your client to it to list available tasks and run named tasks in your project. You will provide your working directory to the client so the server can read your Taskfile.yml and respond with the corresponding tasks you can run.

Step-by-step usage pattern you can follow once the server is running:

Run the server from your environment

uv run --with mcp --directory /path/to/gotask-mcp mcp run /path/to/gotask-mcp/src/server.py

What you can do with the server

Retrieve a list of tasks defined in your Taskfile.yml for the current working directory.
Execute a named task from your Taskfile.yml and monitor its output from the client.