Delete a generated image file
AI agents call delete_image to permanently remove resources in Markdown to Card - MCP工具 — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs permanent deletion of image files without reversal capability. Although the blast radius is constrained to user-owned generated images (not system-critical data), deletion operations are categorically Destructive. Severity is high because careless agent use could remove multiple or important user-generated content, though financial or security impacts are unlikely.
From the tool's definition Tool name is 'delete_image' with description 'Delete a generated image file' — uses the verb 'Delete' and irreversibly removes stored image data.
Attacks that exploit this kind of access
Delete a generated image file. It is categorised as a Destructive tool in the Markdown to Card - MCP工具 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Markdown to Card - MCP工具 MCP server in PolicyLayer and add a rule for delete_image: 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 Markdown to Card - MCP工具. Nothing to install.
delete_image 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_image 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_image. 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_image is provided by the Markdown to Card - MCP工具 MCP server (jasperjeje/mdtcard). 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 →