Tasker MCP

Name: Tasker MCP
Author: dceluis

@dceluis

Repository

About Tasker MCP

An MCP server for Android's Tasker automation app.

#golang #mcp #tasker #tasker-project #mcp-server

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "tasker-mcp": {
      "command": "node",
      "args": [
        "xml-to-tools.js",
        "/path/to/your/exported/mcp_server.prj.xml",
        ">",
        "toolDescriptions.json"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Tasker MCP?

Tasker MCP is an integration that connects Model Context Protocol (MCP)‑enabled applications to Tasker, the Android automation app. It allows AI assistants and other MCP clients to trigger Tasker tasks, flash text, and pass arguments securely via an API key.

How to use Tasker MCP?

Import the Tasker profile (dist/mcp_server.prj.xml) into Tasker and run the MCP generate_api_key task to create an API key.
Select the correct CLI server binary for your device’s architecture (e.g., tasker-mcp-server-cli-aarch64) from the dist/ folder, copy it together with toolDescriptions.json to your device, and rename the binary to mcp-server.
Run the server in SSE mode (./mcp-server --tools <path> --tasker-api-key=tk_... --mode sse) or stdio mode (pipe a JSON‑RPC payload to the binary).
Point your MCP‑enabled app (e.g., Claude Desktop) to the running server using the endpoint or process.

Key features of Tasker MCP

Import a pre‑built Tasker profile for MCP integration
Generate a secure API key for authentication
Run the CLI server in SSE or stdio transport mode
Configurable host, port, and Tasker connection settings
Build the CLI server from source (Go) for custom architecture
Extend the profile with custom tasks using Task Variables and metadata

Use cases of Tasker MCP

Connect Claude Desktop or other MCP clients to Tasker to execute automations
Let an AI assistant flash text, set variables, or trigger complex Tasker actions
Build custom MCP‑enabled workflows by adding Task Variables and exporting updated tool descriptions
Automate device tasks from any application that supports the Model Context Protocol

FAQ from Tasker MCP

How do I generate an API key?

After importing the Tasker profile, run the MCP generate_api_key task inside Tasker – it will produce an API key (e.g., tk_...).

What transport modes are supported?

Two modes: SSE (Server‑Sent Events) and stdio. Use the --mode flag with sse or stdio (default is stdio).

What dependencies do I need?

To build the CLI server yourself you need Go. To generate updated tool descriptions you need Node.js to run the xml-to-tools.js script.

How do I add custom tasks to the MCP profile?

Mark a task as MCP‑enabled by setting its comment (becomes the tool description) and configuring Task Variables that act as arguments. Then copy the special MCP#parse_args action to the top of the task, export the project, and generate a new toolDescriptions.json using node xml-to-tools.js.

Is authentication required?

Yes. The server requires a --tasker-api-key flag that matches the key generated inside Tasker. This key is passed with every request for secure access.