run_gam_command · GAM MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_gam_command does on GAM MCP Server

AI agents invoke run_gam_command to trigger actions in GAM MCP Server. 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_gam_command needs a policy

This is an Execute-category tool because it runs external commands (GAM7 CLI operations) whose effects are contingent on the arguments provided. While the server description mentions capabilities spanning Write (create users/groups) and Destructive (delete/modify) domains, the tool itself is a generic command executor.

From the tool's definition Tool named 'run_gam_command' with empty description on a server that 'Enables AI assistants to perform Google Workspace administrative actions via GAM7'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_gam_command Rate-limited

run_gam_command 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_gam_command": {
      "limits": [
        {
          "counter": "run_gam_command_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 GAM MCP Server, so you can run agents against it safely.

FAQ

Questions about run_gam_command

What does the run_gam_command tool do? +

run_gam_command. It is categorised as a Execute tool in the GAM MCP Server 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_gam_command? +

Register the GAM MCP Server MCP server in PolicyLayer and add a rule for run_gam_command: 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 GAM MCP Server. Nothing to install.

What risk level is run_gam_command? +

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

Can I rate-limit run_gam_command? +

Yes. Add a rate_limit block to the run_gam_command 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_gam_command completely? +

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

run_gam_command is provided by the GAM MCP Server MCP server (ktibbs9417/gamcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.