Remove a trained machine learning model from the GDS model catalog to free memory.
AI agents call drop_model to permanently remove resources in Neo4j Gds — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes trained ML models from the GDS catalog. Once dropped, the model cannot be recovered without retraining. While the data loss is confined to ML models rather than the underlying graph data, the irreversible nature of deletion and the potential business impact (loss of trained models) justifies the 'Destructive' category with 'high' severity.
From the tool's definition Tool name 'drop_model' combined with description 'Remove a trained machine learning model from the GDS model catalog to free memory' indicates irreversible deletion of data (the trained model).
Attacks that exploit this kind of access
Remove a trained machine learning model from the GDS model catalog to free memory. It is categorised as a Destructive tool in the Neo4j Gds MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Neo4j Gds MCP server in PolicyLayer and add a rule for drop_model: 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 Neo4j Gds. Nothing to install.
drop_model 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 drop_model 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 drop_model. 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.
drop_model is provided by the Neo4j Gds MCP server (neo4j-contrib/gds-agent). 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 →