Remove the logo from a museum.
AI agents call delete_museum_logo to permanently remove resources in Confd — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a museum's logo without reverting capability. While the blast radius is somewhat bounded to a single museum's logo asset (not critical organizational data), the irreversible nature of deletion places it in the Destructive category rather than Write. An AI agent misusing this could erase important organizational branding assets.
From the tool's definition Tool name is 'delete_museum_logo' and description states 'Remove the logo from a museum.' The verb 'delete' and 'remove' indicate irreversible deletion of data (a logo asset associated with a museum record).
Attacks that exploit this kind of access
Remove the logo from a museum. It is categorised as a Destructive tool in the Confd MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Confd MCP server in PolicyLayer and add a rule for delete_museum_logo: 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 Confd. Nothing to install.
delete_museum_logo 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_museum_logo 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_museum_logo. 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_museum_logo is provided by the Confd MCP server (mytours/confd-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 →