Delete a step from a card.
AI agents call fizzy_delete_step to permanently remove resources in Fizzy Do MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a step from a card in Fizzy's project management system. Deletion is an irreversible operation that cannot be undone through normal means. While the blast radius is scoped to a single step rather than an entire board or card, the destructive nature of the action and the potential for unintended removal of important task steps justifies the 'high' severity classification.
From the tool's definition Tool name and description: 'fizzy_delete_step' - 'Delete a step from a card.' The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a step from a card. It is categorised as a Destructive tool in the Fizzy Do MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Fizzy Do MCP server in PolicyLayer and add a rule for fizzy_delete_step: 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_delete_step is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the fizzy_delete_step 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_delete_step. 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_delete_step 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 →