Speak a short message back to the user on the active ringback phone call.
AI agents invoke say 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-time operation — transmitting synthesized or text-to-speech audio over an active phone call. It is not merely writing data to a store; it executes an action on a live telephony session whose effects (audio heard by the user) are immediate and depend on the arguments passed. This places it in the Execute category rather than Write.
From the tool's definition Speak a short message back to the user on the active ringback phone call
Documented attack patterns abuse exactly the kind of access say 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 say:
{
"version": "1",
"default": "deny",
"tools": {
"say": {
"limits": [
{
"counter": "say_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}say 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.
Speak a short message back to the user on the active ringback phone call. 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 say: 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.
say 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 say 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 say. 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.
say 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.