Delete a cluster
AI agents call cluster_delete to permanently remove resources in MongoDB Atlas MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes an entire MongoDB cluster, destroying all data and backups associated with it. This is a classic destructive action that cannot be undone and would result in catastrophic data loss if misused by an AI agent. It represents the highest severity risk on the MCP security spectrum.
From the tool's definition Tool name is 'cluster_delete' with description 'Delete a cluster'. The word 'delete' combined with the scope of a database cluster indicates permanent, irreversible removal of infrastructure and data.
Attacks that exploit this kind of access
Delete a cluster. It is categorised as a Destructive tool in the MongoDB Atlas MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MongoDB Atlas MCP Server MCP server in PolicyLayer and add a rule for cluster_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 MongoDB Atlas MCP Server. Nothing to install.
cluster_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 cluster_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 cluster_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.
cluster_delete is provided by the MongoDB Atlas MCP Server MCP server (montumodi/mongodb-atlas-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 →