AI agents use create_drum_pattern to create or update resources in Orpheus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Orpheus environment.
This is a Write operation: it irreversibly adds new MIDI notes/patterns to the project (though reversible via undo in REAPER, the tool itself commits new data structures). It does not execute arbitrary code, delete existing content, or move financial resources.
From the tool's definition Tool creates new MIDI data (drum pattern) from step-grid input. Outputs GM drum notes to channel 9. The word 'create' and the functional description ('Step-grid string → GM drum MIDI') establish that this tool generates and inserts new musical content into…
Attacks that exploit this kind of access
Step-grid string → GM drum MIDI (kick 36 / snare 38 / hat 42, ch9), humanized. It is categorised as a Write tool in the Orpheus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Orpheus MCP server in PolicyLayer and add a rule for create_drum_pattern: 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 Orpheus. Nothing to install.
create_drum_pattern is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_drum_pattern 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 create_drum_pattern. 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.
create_drum_pattern is provided by the Orpheus MCP server (mal0ware/orpheus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →