predict_link_prediction · Neo4j Gds MCP: Risk & Policy

WHAT IT DOES

What predict_link_prediction does on Neo4j Gds

AI agents invoke predict_link_prediction 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.

WHY IT NEEDS A POLICY

Why predict_link_prediction needs a policy

This tool executes a machine learning inference operation (link prediction) on a Neo4j GDS projected graph. It triggers computation using a trained model from the model catalog, which constitutes an external operation with side effects (model execution, result generation). It doesn't merely read static data, nor does it write/delete persistent data irreversibly, so Execute is the most appropriate category.

From the tool's definition 'Predict new relationships in a projected graph using a trained link prediction model' — runs a trained ML model against graph data to generate predictions

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

predict_link_prediction Rate-limited

predict_link_prediction stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "predict_link_prediction": {
      "limits": [
        {
          "counter": "predict_link_prediction_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Neo4j Gds, so you can run agents against it safely.

FAQ

Questions about predict_link_prediction

What does the predict_link_prediction tool do? +

Predict new relationships in a projected graph using a trained link prediction model from the model catalog. 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.

How do I enforce a policy on predict_link_prediction? +

Register the Neo4j Gds MCP server in PolicyLayer and add a rule for predict_link_prediction: 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.

What risk level is predict_link_prediction? +

predict_link_prediction is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit predict_link_prediction? +

Yes. Add a rate_limit block to the predict_link_prediction 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.

How do I block predict_link_prediction completely? +

Set action: deny in the PolicyLayer policy for predict_link_prediction. 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.

What MCP server provides predict_link_prediction? +

predict_link_prediction 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.