Pin a Fizzy card for quick access.
AI agents use fizzy_pin_card to create or update resources in Fizzy Do MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fizzy Do MCP environment.
Pinning a card modifies its display priority or metadata state but does not create, delete, or execute external operations. This is a reversible Write operation with minimal blast radius—unpinning reverses the action. Severity is low because the impact is scoped to card organization and visibility within a task management system, with no data loss or system-wide consequences.
From the tool's definition Tool name 'fizzy_pin_card' and description 'Pin a Fizzy card for quick access' indicate a modification of card metadata/state (pinning status), which is a reversible change to data.
Attacks that exploit this kind of access
Pin a Fizzy card for quick access. It is categorised as a Write tool in the Fizzy Do MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fizzy Do MCP server in PolicyLayer and add a rule for fizzy_pin_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_pin_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_pin_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_pin_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_pin_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 →