script_run · Gworkspace MCP: Risk & Policy

WHAT IT DOES

What script_run does on Gworkspace

AI agents invoke script_run to trigger actions in Gworkspace. 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 script_run needs a policy

This tool runs arbitrary functions in a deployed Google Apps Script, which can perform any action that script permits—file manipulation, email sending, external API calls, data modification, etc. The effects are determined by the script logic and arguments passed, making this Execute rather than Destructive (not inherently irreversible).

From the tool's definition Tool name 'script_run' combined with description 'Execute a function in a deployed script' explicitly indicates code execution capability. The requirement for 'API Executable deployment' confirms this triggers external operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

script_run Rate-limited

script_run 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": {
    "script_run": {
      "limits": [
        {
          "counter": "script_run_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 Gworkspace, so you can run agents against it safely.

FAQ

Questions about script_run

What does the script_run tool do? +

Execute a function in a deployed script. Requires API Executable deployment. It is categorised as a Execute tool in the Gworkspace MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on script_run? +

Register the Gworkspace MCP server in PolicyLayer and add a rule for script_run: 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 Gworkspace. Nothing to install.

What risk level is script_run? +

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

Can I rate-limit script_run? +

Yes. Add a rate_limit block to the script_run 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 script_run completely? +

Set action: deny in the PolicyLayer policy for script_run. 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 script_run? +

script_run is provided by the Gworkspace MCP server (leoonic/gworkspace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.