mcpField
C
Cloud Tasks MCP Server

Cloud Tasks MCP Server

Local
github.com/gitskyfluxCloud & Infra0Updated 79w ago
Repository

About Cloud Tasks MCP Server

Cloud Tasks MCP Server lets AI clients inspect and manage Google Cloud Tasks queues and tasks, including pausing queues and deleting tasks.

Key features

  1. 01List queues and inspect queue details
  2. 02Pause and resume queues
  3. 03List tasks and inspect task details
  4. 04Delete tasks from queues

Use cases

  1. 01Review queues in a Google Cloud location
  2. 02Pause a queue during operations
  3. 03Inspect or remove a queued task

MCP support

It exposes Google Cloud Tasks queue and task operations as tools for MCP clients.

Configuration

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

mcp.json · Universal config
{
  "mcpServers": {
    "cloudtasks": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli"
      ]
    }
  }
}
Run commandnpx -y @smithery/cli

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
npm@smithery/cli

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

Cloud Tasks MCP Server

smithery badge

A Model Context Protocol (MCP) server for Google Cloud Tasks that enables interactions with Google Cloud Tasks queues and tasks.

Features

  • List Cloud Tasks queues in a specified location
  • Get details of a specific queue
  • Pause and resume queues
  • List tasks in a queue
  • Get details of a specific task
  • Delete tasks from a queue

Setup

Installing via Smithery

To install Cloud Tasks Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @gitskyflux/cloudtasks-mcp --client claude
Manual Installation

  1. Install dependencies:

    npm install

  2. Build the project:

    npm run build

  3. Configure Claude Desktop: Add the following to your claude_desktop_config.json:

    "cloudtasks-mcp": {
  "command": "node",
  "args": [
    "/path/to/cloudtasks-mcp/build/index.js"
  ],
  "env": {
    "GOOGLE_CLOUD_LOCATION_PROJECTS": "location:project-id"
  }
}

    Replace the path in args with the actual path to index.js.

    Define a comma-separated list of location:project-id pairs in GOOGLE_CLOUD_LOCATION_PROJECTS. Example: us-east1:google-project-id1,us-central1:google-project-id2 The first listed project is the default.

    The application expects to find .json credential file(s) in the keys folder for each project. Example: keys/google-project-id1.json

    Ensure the relevant cloud service account has appropriate permission to interact with Cloud Tasks, e.g. Cloud Tasks Admin or lesser permission(s).

Available Tools
  • listQueues: List all Cloud Tasks queues in a specified location
  • getQueue: Get details of a specific Cloud Tasks queue
  • pauseQueue: Pause a Cloud Tasks queue
  • resumeQueue: Resume a paused Cloud Tasks queue
  • listTasks: List tasks in a Cloud Tasks queue
  • getTask: Get details of a specific task in a Cloud Tasks queue
  • deleteTask: Delete a task from a Cloud Tasks queue

Example Usage in Claude Desktop

Here are examples of how to use each tool in Claude Desktop:

Pause or Resume a Queue
Pause the special-events queue. Resume the special-events queue.
Get Pending Tasks
How many tasks are currently pending in the special-events queue?
Run a Task in a Paused Queue
Run the task ending with the ID 123456 in the special-events queue.

Development

# Watch mode
npm run dev

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.