Play a Funkwhale track on the paired glasses / phone speaker. Takes a track UUID from fw_search. Returns a streaming envelope that the meta-glasses voice loop intercepts; the LLM should summarize verbally (e.g.
AI agents invoke fw_play 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 — playing audio on a paired device (glasses/phone speaker). It initiates a real-world action on hardware and starts a media stream, making it Execute. Misuse could cause unexpected audio playback on user devices, but the blast radius is limited to audio disruption rather than data loss or financial impact.
From the tool's definition Play a Funkwhale track on the paired glasses / phone speaker... Returns a streaming envelope that the meta-glasses voice loop intercepts
Documented attack patterns abuse exactly the kind of access fw_play 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 fw_play:
{
"version": "1",
"default": "deny",
"tools": {
"fw_play": {
"limits": [
{
"counter": "fw_play_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}fw_play 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.
Play a Funkwhale track on the paired glasses / phone speaker. Takes a track UUID from fw_search. Returns a streaming envelope that the meta-glasses voice loop intercepts; the LLM should summarize verbally (e.g. 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 fw_play: 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.
fw_play 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 fw_play 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 fw_play. 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.
fw_play 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.