hangup_call · Agentline MCP: Risk & Policy

WHAT IT DOES

What hangup_call does on Agentline

AI agents invoke hangup_call to trigger actions in Agentline. 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 hangup_call needs a policy

Hanging up a call is an irreversible external action that terminates live communication. It is not purely destructive (no data deletion), but it executes an external operation with real-world consequences. Misuse could disrupt active 2FA capture or ongoing business calls, making severity high.

From the tool's definition 'End an in-progress call immediately' — terminates an active call session, triggering an external telephony operation with immediate real-world effect

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

hangup_call Rate-limited

hangup_call 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": {
    "hangup_call": {
      "limits": [
        {
          "counter": "hangup_call_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 Agentline, so you can run agents against it safely.

FAQ

Questions about hangup_call

What does the hangup_call tool do? +

End an in-progress call immediately. No-op / error if the call already. It is categorised as a Execute tool in the Agentline MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on hangup_call? +

Register the Agentline MCP server in PolicyLayer and add a rule for hangup_call: 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 Agentline. Nothing to install.

What risk level is hangup_call? +

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

Can I rate-limit hangup_call? +

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

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

hangup_call is provided by the Agentline MCP server (jgottlieb84/agentline-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.