Delete a card
AI agents call planka_delete_card to permanently remove resources in Planka MCP Server for Claude — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a card from a Planka board without the ability to undo the action. Deletion is a destructive operation classified higher than Write (which is reversible). High severity because an AI agent could inadvertently delete important project work, though blast radius is typically scoped to a single card rather than system-wide data.
From the tool's definition Tool name explicitly states 'delete_card' and description confirms 'Delete a card'. Deletion is an irreversible operation that removes data from the kanban board.
Attacks that exploit this kind of access
Delete a card. It is categorised as a Destructive tool in the Planka MCP Server for Claude MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Planka MCP Server for Claude MCP server in PolicyLayer and add a rule for planka_delete_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 Planka MCP Server for Claude. Nothing to install.
planka_delete_card 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 planka_delete_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 planka_delete_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.
planka_delete_card is provided by the Planka MCP Server for Claude MCP server (nextheberg/planka-mcp-server-for-claude). 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 →