browser_endtoend · Limetest MCP Server MCP: Risk & Policy

WHAT IT DOES

What browser_endtoend does on Limetest MCP Server

AI agents invoke browser_endtoend to trigger actions in Limetest MCP Server. 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_endtoend needs a policy

This tool triggers execution of arbitrary browser automation sequences defined in natural language. While the stated purpose is testing, an AI agent could misuse it to interact with live web applications in unintended ways—including accessing sensitive data, submitting forms, or performing unauthorized transactions.

From the tool's definition Tool name 'browser_endtoend' and description 'Run an end to end test suit in the browser' indicate execution of automated browser operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_endtoend Rate-limited

browser_endtoend 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_endtoend": {
      "limits": [
        {
          "counter": "browser_endtoend_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 Limetest MCP Server, so you can run agents against it safely.

FAQ

Questions about browser_endtoend

What does the browser_endtoend tool do? +

Run an end to end test suit in the browser. It is categorised as a Execute tool in the Limetest MCP Server 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_endtoend? +

Register the Limetest MCP Server MCP server in PolicyLayer and add a rule for browser_endtoend: 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 Limetest MCP Server. Nothing to install.

What risk level is browser_endtoend? +

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

Can I rate-limit browser_endtoend? +

Yes. Add a rate_limit block to the browser_endtoend 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_endtoend completely? +

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

browser_endtoend is provided by the Limetest MCP Server MCP server (m2rads/limetest-arch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.