deploy_service_from_image
Deploy a container image from Artifact Registry or Docker Hub as a Cloud Run service.
This record as markdown: /tools/com-googleapis-run-mcp/deploy-service-from-image.md
What deploy_service_from_image does on Google Cloud Run
AI agents invoke deploy_service_from_image to trigger actions in Google Cloud Run. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
service | object | Yes | Required. The service to deploy. |
Parameters from the server's own tool schema.
Why deploy_service_from_image is rated High
This tool executes arbitrary container code in Google Cloud Run, which is a code execution operation with significant blast radius. While it doesn't permanently delete data (Destructive) or move money (Financial), it runs external operations that could modify infrastructure, consume resources, or compromise systems depending on malicious image contents.
From the tool's definition Tool deploys a container image as a Cloud Run service. The description explicitly states 'Deploy a container image...as a Cloud Run service,' indicating execution of containerized code in a managed environment.
Attacks that exploit this kind of access
The rule that runs deploy_service_from_image safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Google Cloud Run, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For deploy_service_from_image, this is the rule to start with:
deploy_service_from_image 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Google Cloud Run, apply this rule, and every deploy_service_from_image call is checked against it from then on.
Questions about deploy_service_from_image
Deploy a container image from Artifact Registry or Docker Hub as a Cloud Run service. It is categorised as a Execute tool in the Google Cloud Run MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
deploy_service_from_image accepts 1 parameter: service. Required: service. The full parameter table on this page comes from the server's own tool schema.
Register the Google Cloud Run MCP server in PolicyLayer and add a rule for deploy_service_from_image: 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 Google Cloud Run. Nothing to install.
deploy_service_from_image is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the deploy_service_from_image 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.
Set action: deny in the PolicyLayer policy for deploy_service_from_image. 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.
deploy_service_from_image is provided by the Google Cloud Run MCP server (https://run.googleapis.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Google Cloud Run, and thousands of servers like it.
Across the catalogue