send_program_change · Midi MCP: Risk & Policy

WHAT IT DOES

What send_program_change does on Midi

AI agents invoke send_program_change to trigger actions in Midi. 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 send_program_change needs a policy

This tool sends a MIDI Program Change message to external hardware instruments, triggering an external operation (changing the active patch/program on a synthesizer or drum machine). It does not read data, persistently write data, delete anything, or involve financial transactions. The blast radius is low — at worst it changes the active sound preset on a connected MIDI device, which is easily reversible.

From the tool's definition Send a MIDI Program Change message

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_program_change Rate-limited

send_program_change 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": {
    "send_program_change": {
      "limits": [
        {
          "counter": "send_program_change_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 Midi, so you can run agents against it safely.

FAQ

Questions about send_program_change

What does the send_program_change tool do? +

Send a MIDI Program Change message. It is categorised as a Execute tool in the Midi MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_program_change? +

Register the Midi MCP server in PolicyLayer and add a rule for send_program_change: 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 Midi. Nothing to install.

What risk level is send_program_change? +

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

Can I rate-limit send_program_change? +

Yes. Add a rate_limit block to the send_program_change 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 send_program_change completely? +

Set action: deny in the PolicyLayer policy for send_program_change. 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 send_program_change? +

send_program_change is provided by the Midi MCP server (pnilan/midi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.