Speak the provided text and optionally listen for a response. This will speak the given text and then immediately start listening for user input if wait_for_response is True. If wait_for_response is False, it will just speak the text without listening for a response. Args: text: The text to speak...
AI agents invoke reply to trigger actions in Speech MCP. 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.
While this tool does not read/write persistent data or delete anything, it executes external operations (audio playback and microphone capture) that have real-world effects. The tool's behavior is contingent on arguments (the text content and wait_for_response flag), making it Execute rather than Read.
From the tool's definition The tool description states it will 'speak the provided text and then immediately start listening for user input' and 'start listening for user input if wait_for_response is True'.
Documented attack patterns abuse exactly the kind of access reply gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Speech MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for reply:
{
"version": "1",
"default": "deny",
"tools": {
"reply": {
"limits": [
{
"counter": "reply_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}reply 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 the provided text and optionally listen for a response. This will speak the given text and then immediately start listening for user input if wait_for_response is True. If wait_for_response is False, it will just speak the text without listening for a response. Args: text: The text to speak to the user wait_for_response: Whether to wait for and return the user's response (default: True) Returns: If wait_for_response is True: The transcription of the user's response. If wait_for_response is False: A confirmation message that the text was spoken. It is categorised as a Execute tool in the Speech MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Speech MCP server in PolicyLayer and add a rule for reply: 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 Speech MCP. Nothing to install.
reply 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 reply 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 reply. 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.
reply is provided by the Speech MCP server (kvadratni/speech-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Speech MCP, 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 Speech MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.