k_means_clustering · Neo4j Gds MCP: Risk & Policy

WHAT IT DOES

What k_means_clustering does on Neo4j Gds

AI agents invoke k_means_clustering 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 k_means_clustering needs a policy

The tool executes a graph algorithm (K-Means clustering) on a Neo4j database. It runs a computational process against the database, which may write results back to the graph (as is typical in Neo4j GDS). This makes it Execute at minimum, with possible Write side effects depending on the execution mode. No destructive, financial, or purely read-only behavior is indicated by the description alone.

From the tool's definition 'run complex graph algorithms', 'selecting and executing appropriate parameterised graph algorithms', 'K-Means clustering is an unsupervised learning algorithm that is used to solve clustering problems'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

k_means_clustering Rate-limited

k_means_clustering 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": {
    "k_means_clustering": {
      "limits": [
        {
          "counter": "k_means_clustering_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 k_means_clustering

What does the k_means_clustering tool do? +

K-Means clustering is an unsupervised learning algorithm that is used to solve clustering problems. 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 k_means_clustering? +

Register the Neo4j Gds MCP server in PolicyLayer and add a rule for k_means_clustering: 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 k_means_clustering? +

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

Can I rate-limit k_means_clustering? +

Yes. Add a rate_limit block to the k_means_clustering 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 k_means_clustering completely? +

Set action: deny in the PolicyLayer policy for k_means_clustering. 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 k_means_clustering? +

k_means_clustering 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.