browser_assert · AutoDev MCP: Risk & Policy

WHAT IT DOES

What browser_assert does on AutoDev MCP

AI agents invoke browser_assert to trigger actions in AutoDev 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 browser_assert needs a policy

This tool executes browser-based assertions as part of an automated testing framework. While assertions themselves are typically read-like operations (they check state without modifying the application under test), the act of 'running' them in a browser automation context, combined with persistent logging to a database, crosses into Execute category because: (1) the tool triggers automated operations whose effects…

From the tool's definition Tool name is 'browser_assert' and description states it will 'Run browser assertions and persist pass/fail logs'. The term 'run' combined with browser automation context indicates execution of test assertions that interact with browser state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_assert Rate-limited

browser_assert 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": {
    "browser_assert": {
      "limits": [
        {
          "counter": "browser_assert_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 AutoDev MCP, so you can run agents against it safely.

FAQ

Questions about browser_assert

What does the browser_assert tool do? +

Run browser assertions and persist pass/fail logs. It is categorised as a Execute tool in the AutoDev 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 browser_assert? +

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

What risk level is browser_assert? +

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

Can I rate-limit browser_assert? +

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

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

browser_assert is provided by the AutoDev MCP server (rookiejefren/autocoding-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.