launch_stop · Testops MCP: Risk & Policy

WHAT IT DOES

What launch_stop does on Testops

AI agents invoke launch_stop to trigger actions in Testops. 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 launch_stop needs a policy

This tool executes a command to stop an active launch/test run on an external system. While not destructive (the data itself is not deleted), it performs an irreversible operational change — a running test execution cannot be resumed from the same point. The blast radius is high because an AI agent could inadvertently halt critical test runs or disrupt CI/CD pipelines.

From the tool's definition Tool description states 'Close/stop a running launch (ends the run on TestOps)' — this triggers an external operation that terminates a running test execution, affecting the state of a remote system (TestOps).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

launch_stop Rate-limited

launch_stop 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": {
    "launch_stop": {
      "limits": [
        {
          "counter": "launch_stop_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 Testops, so you can run agents against it safely.

FAQ

Questions about launch_stop

What does the launch_stop tool do? +

Close/stop a running launch (ends the run on TestOps). It is categorised as a Execute tool in the Testops MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on launch_stop? +

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

What risk level is launch_stop? +

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

Can I rate-limit launch_stop? +

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

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

launch_stop is provided by the Testops MCP server (@syn7xx/testops-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.