Make a bot speak text during a meeting using text-to-speech
AI agents invoke make_bot_speak to trigger actions in Attendee 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 active external operation — causing a bot to audibly speak in a live meeting via text-to-speech. It is not merely writing data to a store; it executes a real-time action in an ongoing video call that affects all participants. Misuse could involve the bot saying inappropriate or misleading things during a meeting, making it medium severity.
From the tool's definition Make a bot speak text during a meeting using text-to-speech
Documented attack patterns abuse exactly the kind of access make_bot_speak gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Attendee MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for make_bot_speak:
{
"version": "1",
"default": "deny",
"tools": {
"make_bot_speak": {
"limits": [
{
"counter": "make_bot_speak_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}make_bot_speak 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 bot speak text during a meeting using text-to-speech. It is categorised as a Execute tool in the Attendee MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Attendee MCP Server MCP server in PolicyLayer and add a rule for make_bot_speak: 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 Attendee MCP Server. Nothing to install.
make_bot_speak 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 make_bot_speak 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 make_bot_speak. 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.
make_bot_speak is provided by the Attendee MCP Server MCP server (rexposadas/attendee-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Attendee 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.
11 Attendee MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.