agent_stop · Frx Director MCP: Risk & Policy

WHAT IT DOES

What agent_stop does on Frx Director

AI agents invoke agent_stop 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_stop needs a policy

While the tool itself is a control/termination command rather than destructive (progress is persisted), it executes an action that interrupts an external agent's behavior. This fits Execute category: it triggers external operations (agent session termination) whose effects depend on context and could disrupt ongoing workflows.

From the tool's definition Tool stops an agent session mid-execution ('砍掉 worker 当前这一轮' / stop the worker's current round). It terminates an active operation and can trigger subsequent corrective actions via agent_send.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

agent_stop Rate-limited

agent_stop 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_stop": {
      "limits": [
        {
          "counter": "agent_stop_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_stop

What does the agent_stop tool do? +

砍掉 worker 当前这一轮(agentSession.stop)。用在:读到快照发现 worker 正冲向错误路线,想立刻截停并 agent_send 纠正、不想干等它 settle。进展已落盘(ledger/progress.md),停掉不丢持久状态。. 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_stop? +

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

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

Can I rate-limit agent_stop? +

Yes. Add a rate_limit block to the agent_stop 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_stop completely? +

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

agent_stop 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.