フィルタースイープを追加(Auto Filterの周波数を自動変化)
AI agents use add_filter_sweep to create or update resources in Ableton MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ableton MCP environment.
This tool creates/adds automation data for a filter sweep effect in Ableton Live. It modifies the project state by writing automation curves for the Auto Filter frequency parameter. This is reversible (automation can be removed), so it falls under Write rather than Destructive. Misuse could alter a project's sound design unintentionally, giving it medium severity.
From the tool's definition フィルタースイープを追加(Auto Filterの周波数を自動変化)— 'adds' a filter sweep by automating Auto Filter frequency changes
Attacks that exploit this kind of access
フィルタースイープを追加(Auto Filterの周波数を自動変化). It is categorised as a Write tool in the Ableton MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ableton MCP server in PolicyLayer and add a rule for add_filter_sweep: 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 Ableton MCP. Nothing to install.
add_filter_sweep 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 add_filter_sweep 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 add_filter_sweep. 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.
add_filter_sweep is provided by the Ableton MCP server (keigotak/abletonmcp). 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 →