Index / MCP servers / Compute

Compute MCP server

Compute is a remote MCP server that gives an AI agent 29 tools, among them create_instance, delete_instance, get_commitment_basic_info. It answers at https://compute.googleapis.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.

Status
Answering
Tools
29
Official
yes, served from googleapis.com
Reliability
10 of 10 checks
Response time
830 ms
Transport
streamable HTTP
Last checked
18 October 2026

Provides capabilities that let LLM agents perform a range of infrastructure management tasks.

Description as the publisher wrote it.

The 29 tools Compute offers

ToolWhat it does
create_instanceCreate a new Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as input. If machine_type is not provided, it defaults to `e2-medium`. If image_project and image_family are not provided, it defaul
Inputs: guestAccelerators, imageFamily, imageProject, machineType, maintenancePolicy, name
delete_instanceDelete a Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as input. Proceed only if there is no error in response and the status of the operation is `DONE` without any errors. To get details of
Inputs: name, project, zone
get_commitment_basic_infoGet basic information about a Compute Engine Commitment, including its name, ID, status, plan, type, resources, and creation, start and end timestamps. Requires project, region, and commitment name as input.
Inputs: name, project, region
get_disk_basic_infoGet basic information about a Compute Engine disk, including its name, ID, description, creation timestamp, size, type, status, last attach timestamp, and last detach timestamp. Requires project, zone, and disk name as input.
Inputs: name, project, zone
get_disk_performance_configGet performance configuration of a Compute Engine disk, including its type, size, provisioned IOPS, provisioned throughput, physical block size, storage pool and access mode. Requires project, zone, and disk name as input.
Inputs: name, project, zone
get_instance_basic_infoGet basic information about a Compute Engine VM instance, including its name, ID, status, machine type, creation timestamp, and attached guest accelerators. Requires project, zone, and instance name as input.
Inputs: name, project, zone
get_instance_group_manager_basic_infoGet basic information about a Compute Engine managed instance group (MIG), including its name, ID, instance template, base instance name, target size, target stopped size, target suspended size, status and creation timestamp. Requires proje
Inputs: name, project, zone
get_instance_template_basic_infoGet basic information about a Compute Engine instance template, including its name, ID, description, machine type, region, and creation timestamp. Requires project and instance template name as input.
Inputs: name, project
get_instance_template_propertiesGet instance properties of a Compute Engine instance template. This includes properties such as description, tags, machine type, network interfaces, disks, metadata, service accounts, scheduling options, labels, guest accelerators, reservat
Inputs: name, project
get_reservation_basic_infoGet Compute Engine reservation basic info including name, ID, creation timestamp, zone, status, specific reservation required, commitment, and linked commitments. Requires project, zone, and reservation name as input.
Inputs: name, project, zone
get_reservation_detailsGet Compute Engine reservation details. Returns reservation details including name, ID, status, creation timestamp, specific reservation properties like machine type, guest accelerators and local SSDs, aggregate reservation properties like
Inputs: name, project, zone
get_zone_operationGet details of a zone operation, including its id, name, status, creation timestamp, error, warning, HTTP error message and HTTP error status code. Requires project, zone, and operation name as input.
Inputs: name, project, zone
list_accelerator_typesLists the available Google Compute Engine accelerator types. Requires project and zone as input. Returns accelerator types, including id, creation timestamp, name, description, deprecated, zone, and maximum cards per instance.
Inputs: project, zone
list_commitment_reservationsLists reservations for a Compute Engine Commitment. Returns reservation details including name, ID, status, creation timestamp, specific reservation properties like machine type, guest accelerators and local SSDs, aggregate reservation prop
Inputs: name, project, region
list_commitmentsLists Compute Engine Commitments in a region. Details for each commitment include name, ID, status, plan, type, resources, and creation, start and end timestamps. Requires project and region as input.
Inputs: pageSize, pageToken, project, region
list_disksLists Compute Engine disks. Details for each disk include name, ID, description, creation timestamp, size, type, status, last attach timestamp, and last detach timestamp. Requires project and zone as input.
Inputs: pageSize, pageToken, project, zone
list_imagesLists Compute Engine Images. Details for each image include name, ID, status, family, and creation timestamp. Requires project as input.
Inputs: pageSize, pageToken, project
list_instance_attached_disksLists the disks attached to a Compute Engine virtual machine (VM) instance. For each attached disk, the response includes details such as kind, type, mode, saved state, source, device name, index, boot, initialize parameters, auto delete, l
Inputs: name, project, zone
list_instance_group_managersLists Compute Engine managed instance groups (MIGs). Details for each MIG include name, ID, instance template, base instance name, target size, target stopped size, target suspended size, status and creation timestamp. Requires project and
Inputs: pageSize, pageToken, project, zone
list_instance_templatesLists Compute Engine instance templates. Details for each instance template include name, ID, description, machine type, region, and creation timestamp. Requires project as input.
Inputs: pageSize, pageToken, project
list_instancesLists Compute Engine virtual machine (VM) instances. Details for each instance include name, ID, status, machine type, creation timestamp, and attached guest accelerators. Use other tools to get more details about each instance. Requires pr
Inputs: pageSize, pageToken, project, zone
list_machine_typesLists the available Google Compute Engine machine types. Requires project and zone as input. Returns machine types, including id, creationTimestamp, name, description, guest cpus, memory, image space, maximum persistent disks, maximum persi
Inputs: project, zone
list_managed_instancesLists managed instances for a given managed instance group (MIG). For each instance, details include id, instance URL, instance status, and current action. Requires project, zone, and MIG name as input.
Inputs: name, pageSize, pageToken, project, zone
list_reservationsLists Compute Engine reservations. Details for each reservation include name, ID, creation timestamp, zone, status, specific reservation required, commitment, and linked commitments. Requires project and zone as input.
Inputs: pageSize, pageToken, project, zone
list_snapshotsLists snapshots in a project providing basic information per snapshot including name, id, status, creation time, disk size, storage bytes, source disk, and source disk id. Requires project as input.
Inputs: pageSize, pageToken, project
reset_instanceResets a Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as input. Proceed only if there is no error in response and the status of the operation is `DONE` without any errors. To get details of
Inputs: name, project, zone
set_instance_machine_typeSets the machine type for a stopped Google Compute Engine instance to the specified machine type. Requires project, zone, instance name and machine type as input. Proceed only if there is no error in response and the status of the operation
Inputs: machineType, name, project, zone
start_instanceStarts a Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as input. Proceed only if there is no error in response and the status of the operation is `DONE` without any errors. To get details of
Inputs: name, project, zone
stop_instanceStops a Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as input. Proceed only if there is no error in response and the status of the operation is `DONE` without any errors. To get details of t
Inputs: name, project, zone

Add Compute to your AI client

Every block below points at https://compute.googleapis.com/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http compute https://compute.googleapis.com/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "compute": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://compute.googleapis.com/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "compute": {
      "url": "https://compute.googleapis.com/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "compute": {
      "type": "http",
      "url": "https://compute.googleapis.com/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "compute": {
      "url": "https://compute.googleapis.com/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "compute": {
      "serverUrl": "https://compute.googleapis.com/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "compute": {
      "url": "https://compute.googleapis.com/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: Compute
version: 0.0.1
schema: v1
mcpServers:
  - name: Compute
    type: streamable-http
    url: https://compute.googleapis.com/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "compute": {
      "httpUrl": "https://compute.googleapis.com/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "compute": {
      "type": "http",
      "url": "https://compute.googleapis.com/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "compute": {
      "url": "https://compute.googleapis.com/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fcompute.googleapis.com%2Fmcp&type=streamable_http&id=compute&name=Compute

Is Compute up right now?

It answered our last check on 18 October 2026 in 830 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Compute

Questions about Compute

Is there an official Compute MCP server?

Yes. It is published by googleapis.com and served from compute.googleapis.com, the vendor's own domain: https://compute.googleapis.com/mcp.

How many tools does Compute have?

29, as returned by the server's own tools/list on 31 August 2026: create_instance, delete_instance, get_commitment_basic_info, get_disk_basic_info, get_disk_performance_config, get_instance_basic_info, get_instance_group_manager_basic_info, get_instance_template_basic_info, and 21 more.

Is Compute down?

It answered our last check on 18 October 2026 in 830 ms. Over 10 checks since 5 September 2026 it answered 10.

How do I add Compute to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://compute.googleapis.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Compute need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: com.googleapis.compute. Endpoint host: compute.googleapis.com. ARD identifier: urn:air:com.googleapis.compute:mcp:mcp. First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.