agent_tools · Frx Director MCP: Risk & Policy

WHAT IT DOES

What agent_tools does on Frx Director

AI agents invoke agent_tools to trigger actions in Frx Director. 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 agent_tools needs a policy

This tool enables execution of powerful reverse-engineering operations against web pages and browser internals. While the tool itself is a listing/metadata function (which would normally be Read), its purpose is to expose and provide access to execute 16 distinct reverse-engineering tools that manipulate browser behavior, inspect protected code, and bypass security mechanisms.

From the tool's definition Tool provides access to 16 engine-level reverse-engineering tools including 'signer_trace', 'jsvmp_trace', 'closure_read', 'webapi_trace', 'whitebox_diff', 'wasm_probe' and others.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

agent_tools Rate-limited

agent_tools 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": {
    "agent_tools": {
      "limits": [
        {
          "counter": "agent_tools_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 Frx Director, so you can run agents against it safely.

FAQ

Questions about agent_tools

What does the agent_tools tool do? +

列出浏览器侧可用的逆向工具清单(名称/说明/是否需确认/参数名)——含 16 个引擎级逆向工具(signer_trace/jsvmp_trace/closure_read/webapi_trace/whitebox_diff/wasm_probe 等,页面检测不到)。. It is categorised as a Execute tool in the Frx Director MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on agent_tools? +

Register the Frx Director MCP server in PolicyLayer and add a rule for agent_tools: 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 Frx Director. Nothing to install.

What risk level is agent_tools? +

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

Can I rate-limit agent_tools? +

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

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

agent_tools is provided by the Frx Director MCP server (whitenightshadow/frx-director-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.