detach_debugger · Browser MCP Bridge MCP: Risk & Policy

WHAT IT DOES

What detach_debugger does on Browser MCP Bridge

AI agents invoke detach_debugger to trigger actions in Browser MCP Bridge. 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 detach_debugger needs a policy

Detaching a debugger is an external operation that modifies the debugging session state of a browser tab. It is not a simple read, nor does it delete data, but it triggers an operational change (terminating a debugger attachment) that affects external system state. This falls under Execute as it triggers an external operation. Misuse could disrupt active debugging sessions or monitoring, hence medium severity.

From the tool's definition Detach Chrome debugger from a tab

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

detach_debugger Rate-limited

detach_debugger 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": {
    "detach_debugger": {
      "limits": [
        {
          "counter": "detach_debugger_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 Browser MCP Bridge, so you can run agents against it safely.

FAQ

Questions about detach_debugger

What does the detach_debugger tool do? +

Detach Chrome debugger from a tab. It is categorised as a Execute tool in the Browser MCP Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on detach_debugger? +

Register the Browser MCP Bridge MCP server in PolicyLayer and add a rule for detach_debugger: 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 Browser MCP Bridge. Nothing to install.

What risk level is detach_debugger? +

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

Can I rate-limit detach_debugger? +

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

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

detach_debugger is provided by the Browser MCP Bridge MCP server (robhicks/browser-mcp-bridge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.