Generate or retrieve TTS audio for an article. Requires node-edge-tts package (npm install node-edge-tts).
AI agents call crow_media_listen to retrieve information from Crow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool generates or retrieves text-to-speech audio content. The 'retrieve' aspect is clearly a Read operation, and 'generate' here means synthesizing audio from existing text rather than creating/modifying persistent data. No side effects beyond possibly caching the generated audio are implied. Low severity as misuse would at most waste compute resources or expose article content.
From the tool's definition Generate or retrieve TTS audio for an article
Documented attack patterns abuse exactly the kind of access crow_media_listen gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for crow_media_listen:
{
"version": "1",
"default": "deny",
"tools": {
"crow_media_listen": {}
}
} crow_media_listen is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generate or retrieve TTS audio for an article. Requires node-edge-tts package (npm install node-edge-tts). It is categorised as a Read tool in the Crow MCP Server, which means it retrieves data without modifying state.
Register the Crow MCP server in PolicyLayer and add a rule for crow_media_listen: 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 Crow. Nothing to install.
crow_media_listen 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 crow_media_listen 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 crow_media_listen. 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.
crow_media_listen is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, 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.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.