compute
RemoteAbout compute
Provides capabilities that let LLM agents perform a range of infrastructure management tasks
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://compute.googleapis.com/mcpclaude mcp add --transport http com-googleapis-compute https://compute.googleapis.com/mcp{"mcpServers":{"com-googleapis-compute":{"type":"http","url":"https://compute.googleapis.com/mcp"}}}Open in Cursor{"servers":{"com-googleapis-compute":{"type":"http","url":"https://compute.googleapis.com/mcp"}}}Open in VS Code{"mcpServers":{"com-googleapis-compute":{"type":"http","url":"https://compute.googleapis.com/mcp"}}}{"mcpServers":{"com-googleapis-compute":{"serverUrl":"https://compute.googleapis.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
29| Parameter | Type | Required | Description |
|---|---|---|---|
| name | string | Yes | Required. Identifier. The instance name. |
| zone | string | Yes | Required. The zone of the instance. |
| project | string | Yes | Required. Project ID for this request. |
| imageFamily | string | No | Optional. The image family of the instance. |
| machineType | string | No | Optional. The machine type of the instance. |
| imageProject | string | No | Optional. The image project of the instance. |
| guestAccelerators | array | No | Optional. The list of attached accelerators. Each entry specifies the accelerator type (short name or full/partial URL, e.g., 'nvidia-tesla-p4') and the count. |
| maintenancePolicy | enum | No | Optional. The maintenance policy option for the instance.MIGRATE | TERMINATE |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
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.