Set the IP address and port of the Sushi server.
AI agents use set_sushi_server to create or update resources in Sushi MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sushi MCP Server environment.
This tool creates or modifies configuration data (network endpoint settings) in a reversible manner. While it doesn't delete data or execute arbitrary code, changing the server connection parameters could redirect audio processing to an unintended server, affecting the entire audio pipeline.
From the tool's definition set_sushi_server modifies the configuration of the Sushi audio engine connection parameters (IP address and port), which are stored settings that control how the system connects to the audio server.
Attacks that exploit this kind of access
Set the IP address and port of the Sushi server. It is categorised as a Write tool in the Sushi MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sushi MCP Server MCP server in PolicyLayer and add a rule for set_sushi_server: 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.
set_sushi_server is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_sushi_server 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 set_sushi_server. 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.
set_sushi_server 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 →