close_midi_port · Midi MCP: Risk & Policy

WHAT IT DOES

What close_midi_port does on Midi

AI agents use close_midi_port to create or update resources in Midi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Midi environment.

WHY IT NEEDS A POLICY

Why close_midi_port needs a policy

Closing a MIDI port is a reversible action that modifies connection state (the port can be reopened). It does not delete data, execute code, or move money. It falls under Write as it changes the state of a resource. Severity is low since the worst-case impact is disruption of MIDI communication, which is easily restored by reopening the port.

From the tool's definition Close the currently open MIDI port

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

close_midi_port Rate-limited

close_midi_port stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "close_midi_port": {
      "limits": [
        {
          "counter": "close_midi_port_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 close_midi_port

What does the close_midi_port tool do? +

Close the currently open MIDI port. It is categorised as a Write tool in the Midi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on close_midi_port? +

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

close_midi_port is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit close_midi_port? +

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

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

close_midi_port 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.