Remove a parameter from the watch list for real-time updates.
AI agents use unwatch_parameter 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 modifies the state of a watch list (removes a parameter from monitoring), which is a reversible write operation. It does not delete audio data, execute code, or have financial implications. The blast radius is low as it only affects parameter monitoring, not audio processing itself.
From the tool's definition 'Remove a parameter from the watch list for real-time updates' — modifies a watch list by removing an entry
Attacks that exploit this kind of access
Remove a parameter from the watch list for real-time updates. 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 unwatch_parameter: 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.
unwatch_parameter 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 unwatch_parameter 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 unwatch_parameter. 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.
unwatch_parameter 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 →