Delete a read from the library.
AI agents call delete_read to permanently remove resources in Mcp Elevenreader — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of library items is an irreversible operation that cannot be undone. This falls squarely into the Destructive category as it permanently removes user data. Severity is high because deleting reads from a library could result in loss of user's reading progress, bookmarks, or documents, though the blast radius is typically limited to one user's library rather than system-wide data.
From the tool's definition Tool name 'delete_read' explicitly indicates deletion operation. Description states 'Delete a read from the library' - direct confirmation of irreversible removal of data.
Attacks that exploit this kind of access
Delete a read from the library. It is categorised as a Destructive tool in the Mcp Elevenreader MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Elevenreader MCP server in PolicyLayer and add a rule for delete_read: 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 Mcp Elevenreader. Nothing to install.
delete_read 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_read 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_read. 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_read is provided by the Mcp Elevenreader MCP server (mit9/mcp-elevenreader). 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 →