Run a REAPER action by command ID.
AI agents invoke run_action to trigger actions in Reaper. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool permits execution of external operations (REAPER actions) whose effects are determined by the argument (command ID). While individual REAPER actions may be benign, the tool's design allows an AI to invoke any command ID, potentially including destructive operations (delete tracks, overwrite files), system calls, or other irreversible changes.
From the tool's definition "Run a REAPER action by command ID" — the tool executes arbitrary actions in REAPER DAW based on command IDs, which can trigger any operation the DAW supports, including destructive edits, audio processing, or system commands.
Documented attack patterns abuse exactly the kind of access run_action gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Reaper, and nothing reaches the server without passing your rules. This is the rule we recommend for run_action:
{
"version": "1",
"default": "deny",
"tools": {
"run_action": {
"limits": [
{
"counter": "run_action_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_action stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run a REAPER action by command ID. It is categorised as a Execute tool in the Reaper MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Reaper MCP server in PolicyLayer and add a rule for run_action: 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 Reaper. Nothing to install.
run_action is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_action 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 run_action. 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.
run_action is provided by the Reaper MCP server (twelvetake-studios/reaper-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Reaper, 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.
158 Reaper tools catalogued and risk-classified — across an index of 43,000+ MCP servers.