assert_run · Assert MCP: Risk & Policy

WHAT IT DOES

What assert_run does on Assert

AI agents invoke assert_run to trigger actions in Assert. 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 assert_run needs a policy

This tool executes external operations (browser automation via Playwright) whose effects depend on the test scenario arguments. While the primary intent is testing, an AI agent could be tricked into running malicious test scenarios that interact with real web applications, steal credentials, modify data, or trigger unwanted transactions. The blast radius is high because Playwright has full browser control.

From the tool's definition Tool description states 'Execute a test scenario' and 'Runs are async' — this triggers Playwright browser automation to perform arbitrary actions defined by the test scenario.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

assert_run Rate-limited

assert_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": {
    "assert_run": {
      "limits": [
        {
          "counter": "assert_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 Assert, so you can run agents against it safely.

FAQ

Questions about assert_run

What does the assert_run tool do? +

Execute a test scenario and return a run ID. Accepts either a saved scenario_id or ad-hoc markdown. Runs are async — use assert_status to poll for completion. It is categorised as a Execute tool in the Assert MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on assert_run? +

Register the Assert MCP server in PolicyLayer and add a rule for assert_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 Assert. Nothing to install.

What risk level is assert_run? +

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

Can I rate-limit assert_run? +

Yes. Add a rate_limit block to the assert_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 assert_run completely? +

Set action: deny in the PolicyLayer policy for assert_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 assert_run? +

assert_run is provided by the Assert MCP server (pixel-funnel/assert-click-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.