Start a new phone call via Voyp API. The API returns the call id and a URL where users can track the progress of the call
AI agents invoke start_call to trigger actions in Voyp 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 executes a telephony action that initiates contact with external phone numbers. While not destructive or financial in itself, it represents a significant execute-class capability because: (1) it triggers external real-world operations, (2) the effects are irreversible once initiated, (3) misuse could enable harassment, scam calling, or unauthorized communications.
From the tool's definition Tool description states 'Start a new phone call via Voyp API', which initiates an external telephony operation.
Documented attack patterns abuse exactly the kind of access start_call gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Voyp MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for start_call:
{
"version": "1",
"default": "deny",
"tools": {
"start_call": {
"limits": [
{
"counter": "start_call_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_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.
Free to start. No card required.
Start a new phone call via Voyp API. The API returns the call id and a URL where users can track the progress of the call. It is categorised as a Execute tool in the Voyp MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Voyp MCP Server MCP server in PolicyLayer and add a rule for start_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 Voyp MCP Server. Nothing to install.
start_call 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 start_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.
Set action: deny in the PolicyLayer policy for start_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.
start_call is provided by the Voyp MCP Server MCP server (paulotaylor/voyp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Voyp 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.
7 Voyp MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.