gcloud_deploy_service · Gcloud MCP: Risk & Policy

WHAT IT DOES

What gcloud_deploy_service does on Gcloud

AI agents invoke gcloud_deploy_service to trigger actions in Gcloud. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why gcloud_deploy_service needs a policy

Deploying a service revision is an Execute action because it triggers external operations (Cloud Run deployment) whose effects depend on the arguments (which image, which service, etc.). While it modifies data (service configuration), it is not reversible in the Destructive sense—deployments can be rolled back or updated.

From the tool's definition Tool description explicitly states 'Deploy a new revision to a Cloud Run service by updating the container image' and warns 'This modifies a live service — use with care.' The deploy operation executes a container deployment to production infrastructure.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gcloud_deploy_service Rate-limited

gcloud_deploy_service stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "gcloud_deploy_service": {
      "limits": [
        {
          "counter": "gcloud_deploy_service_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Gcloud, so you can run agents against it safely.

FAQ

Questions about gcloud_deploy_service

What does the gcloud_deploy_service tool do? +

Deploy a new revision to a Cloud Run service by updating the container image. WARNING: This modifies a live service — use with care. It is categorised as a Execute tool in the Gcloud MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on gcloud_deploy_service? +

Register the Gcloud MCP server in PolicyLayer and add a rule for gcloud_deploy_service: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gcloud. Nothing to install.

What risk level is gcloud_deploy_service? +

gcloud_deploy_service is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit gcloud_deploy_service? +

Yes. Add a rate_limit block to the gcloud_deploy_service rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block gcloud_deploy_service completely? +

Set action: deny in the PolicyLayer policy for gcloud_deploy_service. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides gcloud_deploy_service? +

gcloud_deploy_service is provided by the Gcloud MCP server (prmichaelsen/gcloud-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.