voice_call · Telephony MCP Server MCP: Risk & Policy

WHAT IT DOES

What voice_call does on Telephony MCP Server

AI agents invoke voice_call to trigger actions in Telephony MCP Server. 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 voice_call needs a policy

This tool initiates an outbound voice call to a specified phone number, which is an external side-effectful operation. It is not purely destructive or financial, but it executes a real-world action (placing a phone call) whose effects depend on the arguments provided (the target number and call content). Misuse could involve harassment, toll fraud, or unwanted calls to arbitrary numbers, making the blast radius high.

From the tool's definition 'Make a voice call or phone call to a given number' - triggers an external real-world telephony operation via Vonage API

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

voice_call Rate-limited

voice_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": {
    "voice_call": {
      "limits": [
        {
          "counter": "voice_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 Telephony MCP Server, so you can run agents against it safely.

FAQ

Questions about voice_call

What does the voice_call tool do? +

Make a voice call or phone call to a given number. Accepts prompts like. It is categorised as a Execute tool in the Telephony MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on voice_call? +

Register the Telephony MCP Server MCP server in PolicyLayer and add a rule for voice_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 Telephony MCP Server. Nothing to install.

What risk level is voice_call? +

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

Can I rate-limit voice_call? +

Yes. Add a rate_limit block to the voice_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 voice_call completely? +

Set action: deny in the PolicyLayer policy for voice_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 voice_call? +

voice_call is provided by the Telephony MCP Server MCP server (vonage-community/telephony-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.