agent_send · Frx Director MCP: Risk & Policy

WHAT IT DOES

What agent_send does on Frx Director

AI agents invoke agent_send 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_send needs a policy

This tool sends a directive message to the agent and advances the execution harness to the next round. It triggers active agent execution (the worker model runs tools based on the message), making it Execute rather than Write. Misuse could cause the agent to perform arbitrary browser-based reverse-engineering actions, hence high severity.

From the tool's definition 把方向纠正作为下一条 user 消息发出去并起下一轮(=harness 的 advance) — sends a message and triggers the next agent execution round

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

agent_send Rate-limited

agent_send 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_send": {
      "limits": [
        {
          "counter": "agent_send_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_send

What does the agent_send tool do? +

★director 的核心动作:把方向纠正作为下一条 user 消息发出去并起下一轮(=harness 的 advance)。. 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_send? +

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

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

Can I rate-limit agent_send? +

Yes. Add a rate_limit block to the agent_send 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_send completely? +

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

agent_send 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.