Get the number of MIDI input and output ports.
AI agents call get_midi_ports to retrieve information from Sushi MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves metadata about MIDI port availability—a non-destructive, informational query. It has no side effects, cannot modify state, and presents minimal security risk. A misused call would at worst expose harmless MIDI port configuration details.
From the tool's definition Tool name 'get_midi_ports' and description 'Get the number of MIDI input and output ports' indicate a read-only query operation that retrieves system information about available MIDI ports without modification.
Attacks that exploit this kind of access
Get the number of MIDI input and output ports. It is categorised as a Read tool in the Sushi MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sushi MCP Server MCP server in PolicyLayer and add a rule for get_midi_ports: 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 Sushi MCP Server. Nothing to install.
get_midi_ports is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_midi_ports 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.
Set action: deny in the PolicyLayer policy for get_midi_ports. 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.
get_midi_ports is provided by the Sushi MCP Server MCP server (nagarjun226/sushi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →