Send a text line to be spoken through paired glasses. Requires the user to have at least one glasses device paired and online. Returns a hint string only — the panel handles delivery via WebSocket.
AI agents invoke crow_glasses_speak to trigger actions in Crow. 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 operation — causing paired glasses hardware to speak audio output. It is not merely reading or writing data; it actively executes an action on a physical/external device (text-to-speech via WebSocket delivery).
From the tool's definition Send a text line to be spoken through paired glasses... handles delivery via WebSocket
Documented attack patterns abuse exactly the kind of access crow_glasses_speak 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_glasses_speak:
{
"version": "1",
"default": "deny",
"tools": {
"crow_glasses_speak": {
"limits": [
{
"counter": "crow_glasses_speak_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}crow_glasses_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.
Send a text line to be spoken through paired glasses. Requires the user to have at least one glasses device paired and online. Returns a hint string only — the panel handles delivery via WebSocket. It is categorised as a Execute tool in the Crow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Crow MCP server in PolicyLayer and add a rule for crow_glasses_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 Crow. Nothing to install.
crow_glasses_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 crow_glasses_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 crow_glasses_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.
crow_glasses_speak 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.