execute_lua · Scythe MCP REAPER MCP: Risk & Policy

WHAT IT DOES

What execute_lua does on Scythe MCP REAPER

AI agents invoke execute_lua to trigger actions in Scythe MCP 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.

WHY IT NEEDS A POLICY

Why execute_lua needs a policy

execute_lua directly runs code with effects determined entirely by the argument (the Lua script content). In the context of REAPER (a powerful DAW with system-level capabilities), executing arbitrary Lua without restrictions poses critical risk: an AI agent could inadvertently delete tracks, corrupt projects, access the file system, or trigger unintended side effects. This is the Execute category by definition.

From the tool's definition Tool is named 'execute_lua' with no description provided. The name unambiguously indicates execution of Lua code.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_lua Rate-limited

execute_lua 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_lua": {
      "limits": [
        {
          "counter": "execute_lua_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Scythe MCP REAPER, so you can run agents against it safely.

FAQ

Questions about execute_lua

What does the execute_lua tool do? +

execute_lua. It is categorised as a Execute tool in the Scythe MCP REAPER MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_lua? +

Register the Scythe MCP REAPER MCP server in PolicyLayer and add a rule for execute_lua: 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.

What risk level is execute_lua? +

execute_lua is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit execute_lua? +

Yes. Add a rate_limit block to the execute_lua 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.

How do I block execute_lua completely? +

Set action: deny in the PolicyLayer policy for execute_lua. 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.

What MCP server provides execute_lua? +

execute_lua 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.