break_on_xhr · JS Reverse MCP: Risk & Policy

WHAT IT DOES

What break_on_xhr does on JS Reverse MCP

AI agents invoke break_on_xhr to trigger actions in JS Reverse 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 break_on_xhr needs a policy

Setting a breakpoint is an active intervention in the browser's execution environment — it halts execution when the condition is met. This is not a passive read; it modifies the debug state and affects runtime behavior. It belongs to Execute rather than Write because it triggers external operations (pausing script execution) whose effects depend on the argument (the URL pattern).

From the tool's definition Sets a breakpoint that triggers when an XHR/Fetch request URL contains the specified string

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

break_on_xhr Rate-limited

break_on_xhr 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": {
    "break_on_xhr": {
      "limits": [
        {
          "counter": "break_on_xhr_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 JS Reverse MCP, so you can run agents against it safely.

FAQ

Questions about break_on_xhr

What does the break_on_xhr tool do? +

Sets a breakpoint that triggers when an XHR/Fetch request URL contains the specified string. It is categorised as a Execute tool in the JS Reverse 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 break_on_xhr? +

Register the JS Reverse MCP server in PolicyLayer and add a rule for break_on_xhr: 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 JS Reverse MCP. Nothing to install.

What risk level is break_on_xhr? +

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

Can I rate-limit break_on_xhr? +

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

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

break_on_xhr is provided by the JS Reverse MCP server (zhizhuodemao/js-reverse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.