Delete a Mango index (CouchDB 3.x+)
AI agents call deleteMangoIndex to permanently remove resources in CouchDB MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a Mango index is an irreversible destructive action that removes query optimization metadata from the database. While not as severe as deleting an entire database or documents, it permanently removes the index structure and cannot be undone without recreation. This falls squarely into the Destructive category due to its permanent nature, even though the data itself remains intact.
From the tool's definition Tool name 'deleteMangoIndex' and description 'Delete a Mango index' indicate irreversible deletion of a database index.
Attacks that exploit this kind of access
Delete a Mango index (CouchDB 3.x+). It is categorised as a Destructive tool in the CouchDB MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CouchDB MCP Server MCP server in PolicyLayer and add a rule for deleteMangoIndex: 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 CouchDB MCP Server. Nothing to install.
deleteMangoIndex 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 deleteMangoIndex 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 deleteMangoIndex. 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.
deleteMangoIndex is provided by the CouchDB MCP Server MCP server (robertoamoreno/couchdb-mcp-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 →