sunvox_render
Offline-render a SunVox/XM/MOD project to audio (wav, or mp3/ogg via ffmpeg), ~130x realtime, up to 20 minutes. Saves it to Crow storage when storage is available and returns the storage_key plus a short-lived storage_url; the local path is returned too. funkwhale_library uploads it to Funkwhale ...
This record as markdown: /tools/kh0pper-crow/sunvox-render.md
What sunvox_render does on Crow
AI agents invoke sunvox_render 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.
Why sunvox_render is rated High
Renders audio files and triggers uploads/notifications; executes multi-step external operations.
From the tool's definition Offline-render a SunVox/XM/MOD project to audio, saves to Crow storage
Attacks that exploit this kind of access
The rule that runs sunvox_render safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Crow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For sunvox_render, this is the rule to start with:
sunvox_render 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Crow, apply this rule, and every sunvox_render call is checked against it from then on.
Questions about sunvox_render
Offline-render a SunVox/XM/MOD project to audio (wav, or mp3/ogg via ffmpeg), ~130x realtime, up to 20 minutes. Saves it to Crow storage when storage is available and returns the storage_key plus a short-lived storage_url; the local path is returned too. funkwhale_library uploads it to Funkwhale so fw_play can play it on the glasses; notify raises a Crow notification when it is done. No audio device needed on this machine. 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 sunvox_render: 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.
sunvox_render 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 sunvox_render 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 sunvox_render. 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.
sunvox_render 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.
More on Crow, and thousands of servers like it.
This server
Across the catalogue