Cloud Tasks MCP Server

What is Cloud Tasks MCP Server?

A Model Context Protocol (MCP) server for Google Cloud Tasks that enables interactions with Google Cloud Tasks queues and tasks. It is designed for use with AI assistants like Claude Desktop to manage task queues programmatically.

How to use Cloud Tasks MCP Server?

Install via Smithery (npx -y @smithery/cli install @gitskyflux/cloudtasks-mcp --client claude) or manually by building the project and adding a configuration entry to claude_desktop_config.json. Set the GOOGLE_CLOUD_LOCATION_PROJECTS environment variable with comma‑separated location:project-id pairs, and place corresponding service account JSON key files in a keys folder.

Key features of Cloud Tasks MCP Server

• 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

Use cases of Cloud Tasks MCP Server

• Pause or resume a specific Cloud Tasks queue on demand
• Retrieve the count of pending tasks in a queue
• Obtain details of a specific task by its ending ID
• Manage queue state directly from an AI assistant conversation

FAQ from Cloud Tasks MCP Server

What does Cloud Tasks MCP Server do?

It acts as a bridge between AI assistants (via the MCP protocol) and Google Cloud Tasks, allowing you to list, get, pause, resume, list tasks, get task details, and delete tasks without leaving the chat interface.

What dependencies or runtime requirements are needed?

The server runs on Node.js and requires service account JSON key files for authentication. It expects a keys folder with one JSON file per project named after the project ID (e.g., keys/google-project-id1.json). The service account must have appropriate Cloud Tasks permissions (e.g., Cloud Tasks Admin).

How do I configure the server for my Google Cloud projects?

Set the GOOGLE_CLOUD_LOCATION_PROJECTS environment variable to a comma‑separated list of location:project-id pairs. The first pair becomes the default project. Example: us-east1:my-project,us-central1:my-project2.

What transports or authentication does it use?

The server uses standard I/O (stdio) as its transport, as configured in the Claude Desktop integration. Authentication is handled via the service account JSON key files placed in the keys folder; the server does not expose any network endpoints.

Are there any known limits or restrictions?

The README does not mention specific limits. However, the server relies on Google Cloud Tasks API quotas and permissions, and operations are limited to the queues and tasks accessible by the configured service accounts.