Delete documents by ids.
AI agents call lucene_delete to permanently remove resources in Mcp Lucene — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes documents from a Lucene index. Deletion is an irreversible operation that cannot be undone without restoration from backups. An AI agent with access to this tool could cause data loss by deleting critical documents if provided with incorrect or malicious IDs.
From the tool's definition Tool name is 'lucene_delete' and description states 'Delete documents by ids.' The verb 'delete' combined with the explicit action of removing documents by their identifiers indicates irreversible data removal.
Attacks that exploit this kind of access
Delete documents by ids. It is categorised as a Destructive tool in the Mcp Lucene MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Lucene MCP server in PolicyLayer and add a rule for lucene_delete: 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 Lucene. Nothing to install.
lucene_delete 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 lucene_delete 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 lucene_delete. 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.
lucene_delete is provided by the Mcp Lucene MCP server (vivekkumarneu/mcp-lucene-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 →