feedback_speak
TTS-summarise the feedback queue via voice_speak. Empty id → summary of the last N reports; id set → read that one report. maxItems defaults to 3.
This record as markdown: /tools/io-github-kivanccakmak-yaver/feedback-speak.md
What feedback_speak does on Yaver
AI agents call feedback_speak to retrieve information from Yaver without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | — | |
device | string | — | Optional target deviceId; empty broadcasts. |
maxItems | integer | — |
Parameters from the server's own tool schema.
Why feedback_speak is rated Low
This tool reads and summarizes feedback reports, converting them to text-to-speech output. It retrieves existing data (feedback queue) without modifying, creating, or deleting anything. The only output is an audio summary of existing reports, making it a read-only operation with low blast radius.
From the tool's definition TTS-summarise the feedback queue via voice_speak. Empty id → summary of the last N reports; id set → read that one report.
Attacks that exploit this kind of access
The rule that runs feedback_speak safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For feedback_speak, this is the rule to start with:
feedback_speak is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every feedback_speak call is checked against it from then on.
Questions about feedback_speak
TTS-summarise the feedback queue via voice_speak. Empty id → summary of the last N reports; id set → read that one report. maxItems defaults to 3. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
feedback_speak accepts 3 parameters: id, device, maxItems. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for feedback_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 Yaver. Nothing to install.
feedback_speak is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the feedback_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 feedback_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.
feedback_speak is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
This server
Across the catalogue