run-gcp-code · GCP MCP: Risk & Policy

WHAT IT DOES

What run-gcp-code does on GCP MCP

AI agents invoke run-gcp-code to trigger actions in GCP MCP. 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 run-gcp-code needs a policy

The tool executes code in a GCP environment with implicit access to multiple high-impact services (compute, storage, databases). Code execution is inherently high-severity because effects depend entirely on argument content; an AI could accidentally or maliciously provision resources, exfiltrate data, or disrupt services.

From the tool's definition Tool name 'run-gcp-code' and description 'Run GCP code' indicate arbitrary code execution capability. Combined with server's access to GCP services (Compute Engine, Cloud Storage, BigQuery), this allows triggering external operations with unrestricted effects…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run-gcp-code Rate-limited

run-gcp-code 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": {
    "run-gcp-code": {
      "limits": [
        {
          "counter": "run-gcp-code_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 GCP MCP, so you can run agents against it safely.

FAQ

Questions about run-gcp-code

What does the run-gcp-code tool do? +

Run GCP code. It is categorised as a Execute tool in the GCP MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run-gcp-code? +

Register the GCP MCP server in PolicyLayer and add a rule for run-gcp-code: 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 GCP MCP. Nothing to install.

What risk level is run-gcp-code? +

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

Can I rate-limit run-gcp-code? +

Yes. Add a rate_limit block to the run-gcp-code 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 run-gcp-code completely? +

Set action: deny in the PolicyLayer policy for run-gcp-code. 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 run-gcp-code? +

run-gcp-code is provided by the GCP MCP server (radiumgu/gcp-ops-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.