AI agents invoke graph_sage_predict to trigger actions in Neo4j Gds. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool runs a machine learning inference operation (GraphSAGE prediction) on a Neo4j graph database. It is not a simple read/query — it executes a trained model to generate embeddings, which constitutes an external computational operation. It doesn't delete data or move money, but it does execute a complex algorithm with side effects (embedding generation, potentially writing results to the graph).
From the tool's definition 'Generates node embeddings using a previously trained GraphSAGE model' — triggers execution of a trained ML model against graph data
Attacks that exploit this kind of access
Generates node embeddings using a previously trained GraphSAGE model from the model catalog (see graph_sage_train). It is categorised as a Execute tool in the Neo4j Gds MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Neo4j Gds MCP server in PolicyLayer and add a rule for graph_sage_predict: 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.
graph_sage_predict is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the graph_sage_predict 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 graph_sage_predict. 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.
graph_sage_predict 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 →