Delete an attachment from a card
AI agents call delete_attachment to permanently remove resources in Mochi MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes an attachment from a card in the Mochi flashcard system. Deletion operations cannot be undone and constitute destructive actions. While the blast radius is somewhat limited to a single attachment rather than entire cards or decks, the permanent loss of potentially important study materials (images, documents, etc.) justifies 'high' severity.
From the tool's definition Tool name contains 'delete' and description states 'Delete an attachment from a card', indicating irreversible removal of data.
Attacks that exploit this kind of access
Delete an attachment from a card. It is categorised as a Destructive tool in the Mochi MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mochi MCP Server MCP server in PolicyLayer and add a rule for delete_attachment: 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 Mochi MCP Server. Nothing to install.
delete_attachment 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 delete_attachment 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 delete_attachment. 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.
delete_attachment is provided by the Mochi MCP Server MCP server (shunkus/mochi-mcp-server). 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 →