drop_graph
AI agents call drop_graph 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.
The 'drop' operation in database systems is a classic destructive action that cannot be undone without restoration from backups. Even though the description is empty, the name alone provides sufficient semantic clarity in a database context. An AI agent misusing this tool could permanently delete valuable graph algorithm results or cached computations.
From the tool's definition Tool name is 'drop_graph' with no description provided. The verb 'drop' in database contexts universally means irreversible deletion.
Attacks that exploit this kind of access
drop_graph. 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_graph: 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_graph 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_graph 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_graph. 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_graph 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 →