Manage collections: list, create, drop, stats, indexes, schema analysis.
AI agents call mongo_collection to permanently remove resources in RedisNexus — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the tool offers read-only operations (list, stats, schema analysis) and reversible write operations (create, indexes), it includes 'drop' which permanently deletes data without undo capability. Destructive category applies when any included action cannot be reversed.
From the tool's definition Tool description explicitly states 'drop' capability alongside other collection management functions like list, create, stats, indexes, and schema analysis. The drop operation irreversibly deletes a MongoDB collection.
Attacks that exploit this kind of access
Manage collections: list, create, drop, stats, indexes, schema analysis. It is categorised as a Destructive tool in the RedisNexus MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RedisNexus MCP server in PolicyLayer and add a rule for mongo_collection: 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 RedisNexus. Nothing to install.
mongo_collection 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 mongo_collection 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 mongo_collection. 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.
mongo_collection is provided by the RedisNexus MCP server (rajkumar-madhu/mcp). 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 →