vibekit_run_qa · Vibekit MCP: Risk & Policy

WHAT IT DOES

What vibekit_run_qa does on Vibekit

AI agents invoke vibekit_run_qa to trigger actions in Vibekit. 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 vibekit_run_qa needs a policy

This tool triggers external operations (QA test execution, screenshot capture, flow testing) whose effects depend on the target app and test parameters. While not destructive or financial, it performs actions beyond simple data retrieval.

From the tool's definition Tool name 'vibekit_run_qa' and description 'Run automated QA tests on a hosted app. Takes a screenshot and tests key flows.' indicate execution of automated test workflows against a live application.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

vibekit_run_qa Rate-limited

vibekit_run_qa 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": {
    "vibekit_run_qa": {
      "limits": [
        {
          "counter": "vibekit_run_qa_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 Vibekit, so you can run agents against it safely.

FAQ

Questions about vibekit_run_qa

What does the vibekit_run_qa tool do? +

Run automated QA tests on a hosted app. Takes a screenshot and tests key flows. It is categorised as a Execute tool in the Vibekit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on vibekit_run_qa? +

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

What risk level is vibekit_run_qa? +

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

Can I rate-limit vibekit_run_qa? +

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

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

vibekit_run_qa is provided by the Vibekit MCP server (vibekit-apps/vibekit-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.