agent_call_tool · Frx Director MCP: Risk & Policy

WHAT IT DOES

What agent_call_tool does on Frx Director

AI agents invoke agent_call_tool 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_call_tool needs a policy

This tool allows a director model to directly execute browser engine tools without intermediary validation or constraints. Browser tools can perform actions like navigation, clicking, form submission, script execution, and other operations whose effects depend entirely on the arguments provided.

From the tool's definition Tool name 'agent_call_tool' combined with description indicating direct execution of browser engine tools ('跑一个浏览器引擎工具' = run a browser engine tool).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

agent_call_tool Rate-limited

agent_call_tool 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_call_tool": {
      "limits": [
        {
          "counter": "agent_call_tool_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_call_tool

What does the agent_call_tool tool do? +

★你(director)亲自跑一个浏览器引擎工具,跳过 DeepSeek worker —— 强模型直驱引擎级工具,比委派 worker 磨更快更准。. 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_call_tool? +

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

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

Can I rate-limit agent_call_tool? +

Yes. Add a rate_limit block to the agent_call_tool 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_call_tool completely? +

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

agent_call_tool 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.