Generate, write, and play a complete pattern in one step. Auto-initializes default browser if needed.
AI agents invoke compose to trigger actions in Strudel MCP Server. 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 generates and plays audio patterns via browser automation, triggering external operations (audio playback, browser initialization). It both writes a pattern and executes it for live playback, making Execute the most severe applicable category. Auto-initializing a browser adds further external side effects beyond simple data writes.
From the tool's definition "Generate, write, and play a complete pattern in one step. Auto-initializes default browser if needed."
Documented attack patterns abuse exactly the kind of access compose gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Strudel MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for compose:
{
"version": "1",
"default": "deny",
"tools": {
"compose": {
"limits": [
{
"counter": "compose_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} compose 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.
Generate, write, and play a complete pattern in one step. Auto-initializes default browser if needed. It is categorised as a Execute tool in the Strudel MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Strudel MCP Server MCP server in PolicyLayer and add a rule for compose: 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 Strudel MCP Server. Nothing to install.
compose 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 compose 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 compose. 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.
compose is provided by the Strudel MCP Server MCP server (williamzujkowski/live-coding-music-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Strudel MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
10 Strudel MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.