send_pitchwheel · Midi MCP: Risk & Policy

WHAT IT DOES

What send_pitchwheel does on Midi

AI agents invoke send_pitchwheel 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_pitchwheel needs a policy

This tool sends a MIDI Pitch Bend message to external hardware (synths, drum machines). It falls under Execute because it triggers an external operation whose effect depends on the pitch bend value argument. The blast radius is low since it only affects audio output on connected MIDI instruments and is easily reversible by sending another message.

From the tool's definition Send a MIDI Pitch Bend message — triggers an external operation (MIDI message) to hardware instruments

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_pitchwheel Rate-limited

send_pitchwheel 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_pitchwheel": {
      "limits": [
        {
          "counter": "send_pitchwheel_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_pitchwheel

What does the send_pitchwheel tool do? +

Send a MIDI Pitch Bend 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_pitchwheel? +

Register the Midi MCP server in PolicyLayer and add a rule for send_pitchwheel: 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_pitchwheel? +

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

Can I rate-limit send_pitchwheel? +

Yes. Add a rate_limit block to the send_pitchwheel 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_pitchwheel completely? +

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

send_pitchwheel 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.