train_link_prediction_model · Neo4j Gds MCP: Risk & Policy

WHAT IT DOES

What train_link_prediction_model does on Neo4j Gds

AI agents use train_link_prediction_model to create or update resources in Neo4j Gds — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Neo4j Gds environment.

WHY IT NEEDS A POLICY

Why train_link_prediction_model needs a policy

This tool trains a machine learning model and persists it to the GDS model catalog. It creates/writes a new artifact (the trained model) but does not delete data, execute arbitrary code, or involve financial transactions. Misuse could waste resources or produce misleading models, giving it medium severity.

From the tool's definition 'Train a link prediction model' and 'store it in the GDS model catalog under modelName'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

train_link_prediction_model Rate-limited

train_link_prediction_model stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "train_link_prediction_model": {
      "limits": [
        {
          "counter": "train_link_prediction_model_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 train_link_prediction_model

What does the train_link_prediction_model tool do? +

Train a link prediction model on a projected graph and store it in the GDS model catalog under modelName. It is categorised as a Write tool in the Neo4j Gds MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on train_link_prediction_model? +

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

What risk level is train_link_prediction_model? +

train_link_prediction_model is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit train_link_prediction_model? +

Yes. Add a rate_limit block to the train_link_prediction_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.

How do I block train_link_prediction_model completely? +

Set action: deny in the PolicyLayer policy for train_link_prediction_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.

What MCP server provides train_link_prediction_model? +

train_link_prediction_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.