run_script_and_wait · RunWhen Platform MCP: Risk & Policy

WHAT IT DOES

What run_script_and_wait does on RunWhen Platform MCP

AI agents invoke run_script_and_wait to trigger actions in RunWhen Platform 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_script_and_wait needs a policy

The tool name 'run_script_and_wait' directly implies executing arbitrary scripts and awaiting their results. This falls under Execute category as it triggers external operations whose effects depend on arguments (the script content). Severity is high because script execution can have wide-ranging side effects depending on what the script does—it could read sensitive data, modify systems, or trigger other operations.

From the tool's definition Tool name 'run_script_and_wait' indicates execution of scripts with waiting for completion. No description provided, but the name clearly indicates code/script execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_script_and_wait Rate-limited

run_script_and_wait 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_script_and_wait": {
      "limits": [
        {
          "counter": "run_script_and_wait_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 RunWhen Platform MCP, so you can run agents against it safely.

FAQ

Questions about run_script_and_wait

What does the run_script_and_wait tool do? +

run_script_and_wait. It is categorised as a Execute tool in the RunWhen Platform 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_script_and_wait? +

Register the RunWhen Platform MCP server in PolicyLayer and add a rule for run_script_and_wait: 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 RunWhen Platform MCP. Nothing to install.

What risk level is run_script_and_wait? +

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

Can I rate-limit run_script_and_wait? +

Yes. Add a rate_limit block to the run_script_and_wait 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_script_and_wait completely? +

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

run_script_and_wait is provided by the RunWhen Platform MCP server (runwhen-contrib/runwhen-platform-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.