agent_start · Frx Director MCP: Risk & Policy

WHAT IT DOES

What agent_start does on Frx Director

AI agents invoke agent_start 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_start needs a policy

This tool triggers the start of a reverse-engineering agent session with significant capabilities including browser navigation, directory creation, and autonomous model execution. While not immediately destructive, it launches code execution in a controlled agent environment.

From the tool's definition Tool description indicates it 'opens a new reverse-engineering session', configures a worker model, disables tool confirmation gates, optionally navigates to a target URL, creates a working directory, and initiates the first round with an AI-assisted mode.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

agent_start Rate-limited

agent_start 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_start": {
      "limits": [
        {
          "counter": "agent_start_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_start

What does the agent_start tool do? +

开一个新的逆向会话:配置 worker 模型(默认沿用浏览器里已配的)+关掉工具确认门、(可选)导航到目标 URL、建工作目录、用便宜的 worker 模型以【AI 辅助模式】发出第一轮(task 作为第 0 条 user)。返回 tid,后续都用它。. 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_start? +

Register the Frx Director MCP server in PolicyLayer and add a rule for agent_start: 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_start? +

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

Can I rate-limit agent_start? +

Yes. Add a rate_limit block to the agent_start 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_start completely? +

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

agent_start 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.