Phone the user and ask them a question out loud, when they are away from the
AI agents invoke ask_user_by_phone to trigger actions in Ringback. 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 operation (placing a phone call) whose effects depend on arguments. It is not merely writing data — it actively causes a phone to ring and audio to be delivered to a person. Misuse could result in harassment, unwanted calls, or disruption. Severity is high because it directly affects a real person in the physical world and cannot be silently undone once the call is placed.
From the tool's definition 'Phone the user and ask them a question out loud' — initiates a live outbound phone call to the user
Documented attack patterns abuse exactly the kind of access ask_user_by_phone gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ringback, and nothing reaches the server without passing your rules. This is the rule we recommend for ask_user_by_phone:
{
"version": "1",
"default": "deny",
"tools": {
"ask_user_by_phone": {
"limits": [
{
"counter": "ask_user_by_phone_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ask_user_by_phone 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.
Phone the user and ask them a question out loud, when they are away from the. It is categorised as a Execute tool in the Ringback MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ringback MCP server in PolicyLayer and add a rule for ask_user_by_phone: 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 Ringback. Nothing to install.
ask_user_by_phone 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 ask_user_by_phone 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 ask_user_by_phone. 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.
ask_user_by_phone is provided by the Ringback MCP server (mohitbadwal/ringback). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ringback, 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.
12 Ringback tools catalogued and risk-classified — across an index of 43,000+ MCP servers.