AI agents call predict_node_classification to retrieve information from Neo4j Gds without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool executes inference on an existing trained model to generate predictions for node classifications. This is a query operation with no side effects—it does not create, modify, delete, or execute arbitrary code. The predictions are derived outputs based on existing trained models and graph data. While it triggers computation, the outcome is deterministic inference rather than arbitrary code execution.
From the tool's definition Tool name and description indicate 'predict' and 'using a trained...model', which are read-only operations that retrieve predictions without modifying the underlying graph or model.
Attacks that exploit this kind of access
Predict class labels for nodes in a projected graph using a trained node classification model from the model catalog. It is categorised as a Read tool in the Neo4j Gds MCP Server, which means it retrieves data without modifying state.
Register the Neo4j Gds MCP server in PolicyLayer and add a rule for predict_node_classification: 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.
predict_node_classification is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the predict_node_classification 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 predict_node_classification. 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.
predict_node_classification 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 →