Add a parameter to the watch list for real-time updates.
AI agents call watch_parameter 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.
The tool watches/monitors a parameter for real-time updates, which is a read operation that observes state without side effects. While it adds to a watch list, the action is passive observation rather than modification of audio processing state, configuration, or data. No destructive, financial, or executable operations are involved. This is informational/monitoring in nature with minimal blast radius if misused.
From the tool's definition Tool name is 'watch_parameter' and description states 'Add a parameter to the watch list for real-time updates.' This operation retrieves or monitors parameter values without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Add a parameter to the watch list for real-time updates. 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 watch_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.
watch_parameter 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 watch_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 watch_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.
watch_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 →