Unsubscribe from notifications for a Fizzy card.
AI agents use fizzy_unwatch_card to create or update resources in Fizzy MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fizzy MCP Server environment.
This tool modifies a subscription/watch state for a card, removing the user from notification recipients. It is a reversible write operation (the user can re-subscribe at any time). No data is deleted, no code is executed, and there are no financial implications. Blast radius is low as it only affects notification preferences.
From the tool's definition Unsubscribe from notifications for a Fizzy card
Attacks that exploit this kind of access
Unsubscribe from notifications for a Fizzy card. It is categorised as a Write tool in the Fizzy MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fizzy MCP Server MCP server in PolicyLayer and add a rule for fizzy_unwatch_card: 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 Fizzy MCP Server. Nothing to install.
fizzy_unwatch_card 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 fizzy_unwatch_card 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 fizzy_unwatch_card. 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.
fizzy_unwatch_card is provided by the Fizzy MCP Server MCP server (ryanyogan/fizzy-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 →