Find and remove duplicate reads (same title). Keeps the oldest one.
AI agents call deduplicate 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.
This tool performs irreversible deletion of documents/reads based on deduplication logic. Even though the deletion is scoped to duplicates, it removes data without the ability to recover deleted items, fitting the Destructive category.
From the tool's definition Tool description states "remove duplicate reads" which explicitly deletes data. The logic of keeping "the oldest one" implies the newer duplicates are irreversibly deleted.
Attacks that exploit this kind of access
Find and remove duplicate reads (same title). Keeps the oldest one. 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 deduplicate: 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.
deduplicate 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 deduplicate 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 deduplicate. 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.
deduplicate 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 →