remove_device
AI agents call remove_device to permanently remove resources in AbletonMCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool name 'remove_device' indicates deletion of a device (instrument or effect) from an Ableton Live track. Based on the sibling tools pattern (delete_clip, delete_scene, delete_track) and the semantics of 'remove', this is likely irreversible. The description is empty, lowering confidence slightly, but context strongly supports a Destructive classification.
From the tool's definition Tool name 'remove_device' strongly implies irreversible removal of a device from a track. Sibling tools include 'delete_clip', 'delete_scene', 'delete_track', confirming a pattern of destructive operations on this server.
Attacks that exploit this kind of access
remove_device. It is categorised as a Destructive tool in the AbletonMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ableton MCP server in PolicyLayer and add a rule for remove_device: 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 AbletonMCP. Nothing to install.
remove_device is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_device 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 remove_device. 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.
remove_device is provided by the Ableton MCP server (milesy1/mcp-ableton-api). 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 →