Make a voice call to a given number and wait for speech input from the recipient. Accepts prompts like
AI agents invoke voice_call_with_input 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.
This tool triggers an external real-world action (placing a phone call) and captures speech input from the recipient. It causes side effects outside the system (telephony network), making it Execute. Severity is high because an AI agent could call arbitrary numbers, potentially harassing recipients, incurring costs, or gathering sensitive speech data without consent.
From the tool's definition 'Make a voice call to a given number and wait for speech input from the recipient' — initiates a real-world telephony operation via Vonage API
Documented attack patterns abuse exactly the kind of access voice_call_with_input gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Telephony MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for voice_call_with_input:
{
"version": "1",
"default": "deny",
"tools": {
"voice_call_with_input": {
"limits": [
{
"counter": "voice_call_with_input_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}voice_call_with_input 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.
Free to start. No card required.
Make a voice call to a given number and wait for speech input from the recipient. 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.
Register the Telephony MCP Server MCP server in PolicyLayer and add a rule for voice_call_with_input: 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.
voice_call_with_input is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the voice_call_with_input 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.
Set action: deny in the PolicyLayer policy for voice_call_with_input. 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.
voice_call_with_input is provided by the Telephony MCP Server MCP server (khan2a/telephony-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Telephony MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Telephony MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.