send_cc · Midi MCP: Risk & Policy

WHAT IT DOES

What send_cc does on Midi

AI agents invoke send_cc 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_cc needs a policy

Sending a MIDI Control Change message executes an external operation that affects the state of connected hardware (synths, drum machines). It is not a simple read or data write — it actively controls physical/electronic instruments in real time. Misuse could cause unintended sound output or hardware parameter changes, warranting medium severity.

From the tool's definition Send a MIDI Control Change message — triggers an external operation (MIDI CC signal) sent to hardware instruments/synthesizers

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_cc Rate-limited

send_cc 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_cc": {
      "limits": [
        {
          "counter": "send_cc_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_cc

What does the send_cc tool do? +

Send a MIDI Control 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_cc? +

Register the Midi MCP server in PolicyLayer and add a rule for send_cc: 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_cc? +

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

Can I rate-limit send_cc? +

Yes. Add a rate_limit block to the send_cc 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_cc completely? +

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

send_cc 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.