Delete notes by id or by key. Returns count/boolean.
AI agents call index-delete to permanently remove resources in MCP Index Notes — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes notes from the index without possibility of recovery (unless external backups exist). Deletion is inherently destructive and cannot be undone. An AI agent misusing this could erase valuable user data. While the blast radius depends on how many notes might be deleted in one call, the irreversible nature and data loss potential warrant 'high' severity.
From the tool's definition Tool description explicitly states 'Delete notes by id or by key' — a clear irreversible deletion operation on stored data.
Attacks that exploit this kind of access
Delete notes by id or by key. Returns count/boolean. It is categorised as a Destructive tool in the MCP Index Notes MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Index Notes MCP server in PolicyLayer and add a rule for index-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 Index Notes. Nothing to install.
index-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 index-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 index-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.
index-delete is provided by the MCP Index Notes MCP server (vjsr007/mcp-index-notes). 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 →