testplan_run · Testops MCP: Risk & Policy

WHAT IT DOES

What testplan_run does on Testops

AI agents invoke testplan_run 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 testplan_run needs a policy

Creating and running a test launch is an Execute action: it initiates automated test operations whose side effects (test runs, resource consumption, external API calls, etc.) depend on the arguments supplied. While the operation is not destructive or financial, it triggers real-world execution that an AI agent could misuse by running inappropriate or resource-intensive tests.

From the tool's definition Tool performs 'Create a launch from a test plan' — this initiates execution of a test plan, which triggers external operations (test execution) whose effects depend on which test plan and launch configuration are provided.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

testplan_run Rate-limited

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

FAQ

Questions about testplan_run

What does the testplan_run tool do? +

Create a launch from a test plan. Body requires launchName. 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 testplan_run? +

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

What risk level is testplan_run? +

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

Can I rate-limit testplan_run? +

Yes. Add a rate_limit block to the testplan_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 testplan_run completely? +

Set action: deny in the PolicyLayer policy for testplan_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 testplan_run? +

testplan_run 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.