AI agents use unarm_all to create or update resources in Ableton — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ableton environment.
This tool changes track properties (armed status) across the session, which constitutes modification of session state. It is reversible (tracks can be rearmed), so it does not qualify as Destructive. It does not execute arbitrary code, delete data, or move financial resources. The medium severity reflects that unarming all tracks could disrupt an active recording session or workflow, but the effect is easily undone.
From the tool's definition The tool modifies track state by unarming all tracks in the session. 'Unarm' indicates changing the armed/record-enabled status of tracks, which is a reversible state modification.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access unarm_all gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ableton, and nothing reaches the server without passing your rules. This is the rule we recommend for unarm_all:
{
"version": "1",
"default": "deny",
"tools": {
"unarm_all": {
"limits": [
{
"counter": "unarm_all_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}unarm_all stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Unarm all tracks in the session. It is categorised as a Write tool in the Ableton 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 unarm_all: 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. Nothing to install.
unarm_all 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 unarm_all 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 unarm_all. 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.
unarm_all is provided by the Ableton MCP server (jpoindexter/ableton-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ableton, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
128 Ableton tools catalogued and risk-classified — across an index of 43,000+ MCP servers.