Subscribe to notifications for a Fizzy card.
AI agents call fizzy_watch_card to retrieve information from Fizzy Do MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or monitors information (notifications) about a card without creating, modifying, or deleting any data. Subscription/notification features are passive read operations with no side effects. The blast radius of misuse is minimal—an attacker could spam notifications or subscribe to unwanted updates, but cannot modify or destroy data.
From the tool's definition "Subscribe to notifications for a Fizzy card" — the tool watches/subscribes to updates without modifying card data, state, or any other system resources.
Attacks that exploit this kind of access
Subscribe to notifications for a Fizzy card. It is categorised as a Read tool in the Fizzy Do MCP MCP Server, which means it retrieves data without modifying state.
Register the Fizzy Do MCP server in PolicyLayer and add a rule for fizzy_watch_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 Do MCP. Nothing to install.
fizzy_watch_card 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 fizzy_watch_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_watch_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_watch_card is provided by the Fizzy Do MCP server (ryanyogan/fizzy-do-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 →