{
  "markdown": "# Compute Engine Managed MCP Extension\n\nThe Compute Engine managed MCP extension provides a comprehensive set of\ncapabilities that let LLM agents perform a range of infrastructure management\ntasks including the following:\n\n-   Manage virtual machine (VM) instances.\n-   Retrieve information about instance group managers, instance templates,\n    disks, snapshots, reservations and commitments.\n\n## Why use the Compute Engine managed MCP server?\n\nGoogle and Google Cloud\n[managed MCP servers](https://docs.cloud.google.com/mcp/overview) can be used in\nyour AI applications with enterprise-ready governance, security, and access\ncontrol.\n\n## Before you begin\n\n1.  In the Google Cloud console, on the\n    [project selector page](https://console.cloud.google.com/projectselector2/home/dashboard),\n    select or create a Google Cloud project.\n\n    > **Note**: If you don't plan to keep the resources that you create in this\n    > procedure, create a project instead of selecting an existing project.\n    > After you finish these steps, you can delete the project, removing all\n    > resources associated with the project.\n\n2.  Get your administrator to grant you the\n    [MCP Tool User role](https://docs.cloud.google.com/iam/docs/roles-permissions/mcp#mcp.toolUser)\n    (`roles/mcp.toolUser`) on the Google Cloud project. If you created a new\n    project, then you already have the required permissions.\n\n3.  Ensure your administrator has enabled the\n    [Compute Engine API](https://console.cloud.google.com/marketplace/product/google/compute.googleapis.com)\n    on the Google Cloud project.\n\n## Configure authentication\n\nThis extension uses Google Application Default Credentials (ADC) to perform\nauthentication. To login with ADC, run the following command in your terminal:\n\n```bash\ngcloud auth application-default login\n```\n\nFor additional details, see the\n[ADC documentation](https://docs.cloud.google.com/docs/authentication/application-default-credentials#personal).\n\n## Install the extension\n\nTo install the extension, run the following command in your terminal:\n\n```bash\ngemini extensions install https://github.com/gemini-cli-extensions/compute-engine\n```\n\n## Available tools\n\nTo see a complete list of available tools and their schemas, see the\n[Compute Engine MCP reference](https://docs.cloud.google.com/compute/docs/reference/mcp).\n\n## Sample use cases\n\nThe following sample use cases describe how you can use the Compute Engine MCP\nserver to manage Compute Engine resources:\n\n-   Inspect and manage resources. For example, to understand resource allocation\n    and configuration in your project, you can list all compute instances. You\n    can also find all running compute instances in a zone that have a specific\n    accelerator attached, and show their location and name for resource\n    management.\n-   Clean up unused resources to reduce operational costs. For example, identify\n    disk snapshots in a zone that are no longer associated with a source disk,\n    or identify and delete stopped VM instances that have costly GPU resources\n    attached.\n-   Optimize instance performance. For example, resize an under-provisioned VM\n    instance to a larger machine type in the same family, and confirm the\n    successful update.\n-   Provision specialized VMs for AI workloads with zone flexibility. For\n    example, create a VM instance with a specific GPU accelerator attached, in\n    any zone in a specified region where it is available.\n-   Troubleshoot and validate instance configurations. For example, retrieve\n    configuration details for a specific VM instance where the job is frozen,\n    reboot it, and confirm the underlying accelerator and disk are attached.\n\n### Sample prompts\n\nThe following are sample prompts that you can use to perform tasks by using the\nCompute Engine MCP server:\n\n-   List all VMs in `PROJECT_ID`, including the VM name and zone.\n-   Show the instance details for `VM_NAME`.\n-   In `REGION`, find all disk snapshots for which the source disk no longer\n    exists.\n-   Change the machine type of `VM_NAME` to the next largest machine type in the\n    same machine family, send notification when it's back online, and confirm\n    the new machine type.\n-   Find all running VMs in `REGION` with NVIDIA accelerators, and show the zone\n    and name for these VMs.\n-   Create a VM in `ZONE` with an NVIDIA T4 accelerator attached. Name the VM\n    my-nvidiat4-vm.\n-   Find all stopped VMs in `REGION` with NVIDIA Tesla T4 accelerators, and\n    delete them.\n\nReplace the following:\n\n-   `PROJECT_ID`: the Google Cloud project ID.\n-   `REGION`: the name of the region where your resources exist.\n-   `ZONE`: the name of the zone where your VMs exist.\n-   `VM_NAME`: the name of your VM instance.\n\n## Optional security and safety configurations\n\nMCP introduces new security risks and considerations due to the wide variety of\nactions that you can take with MCP tools. To minimize and manage these risks,\nGoogle Cloud offers defaults and customizable policies to control the use of MCP\ntools in your Google Cloud organization or project.\n\nFor more information about MCP security and governance, see\n[AI security and safety](https://docs.cloud.google.com/mcp/ai-security-safety).\n\n## Quotas and limits\n\nThe Compute Engine MCP server doesn't have its own quotas. There is no limit on\nthe number of call that can be made to the MCP server. You are still subject to\nthe quotas enforced by the APIs called by the MCP server tools.\n\n## Reference and resources\n\n*   Explore the\n    [Compute Engine remote MCP server reference documentation](https://docs.cloud.google.com/compute/docs/reference/mcp),\n    which includes a list of all available tools, and the full input and output\n    schema for each tool.\n*   See the\n    [Compute Engine overview](https://docs.cloud.google.com/compute/docs).\n*   Learn about\n    [MCP security and governance](https://docs.cloud.google.com/mcp/ai-security-safety).\n",
  "bytes": 5931,
  "sha": "41eaf835ed51b3f6c095590b52e38b6759cacabffae72956da4a863ea56a1d34",
  "repo_slug": "gemini-cli-extensions/compute-engine",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_gemini_cli_extensions_compute_engine_b05f84dc/readme"
}