Create a MIDI item on a track.
AI agents use create_midi_item to create or update resources in Scythe MCP REAPER — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Scythe MCP REAPER environment.
This tool creates new MIDI data within REAPER, which is a reversible modification of the DAW project. It does not execute arbitrary code (that would be execute_lua), delete data, or transfer funds. The severity is medium because misuse could result in unwanted MIDI content added to a project, but this is easily undone/edited.
From the tool's definition Tool name explicitly states 'create_midi_item' and description says 'Create a MIDI item on a track.' The verb 'create' indicates data creation.
Attacks that exploit this kind of access
Create a MIDI item on a track. It is categorised as a Write tool in the Scythe MCP REAPER MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Scythe MCP REAPER MCP server in PolicyLayer and add a rule for create_midi_item: 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 Scythe MCP REAPER. Nothing to install.
create_midi_item 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_midi_item 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_midi_item. 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_midi_item is provided by the Scythe MCP REAPER MCP server (yura9011/scythe_mcp_reaper). 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 →