AI agents call approximate_maximum_k_cut 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 runs a graph algorithm (approximate maximum k-cut) to analyze community structure. Like sibling tools (betweenness_centrality, closeness_centrality, articulation_points), it reads graph data and returns computed results. There is no indication it writes back results to the database or modifies any data. Severity is low since misuse at most wastes compute resources on a read-only query.
From the tool's definition A k-cut of a graph is an assignment of its nodes into k disjoint communities — this describes a graph analysis/query algorithm that computes a partition of nodes without modifying or deleting data.
Attacks that exploit this kind of access
A k-cut of a graph is an assignment of its nodes into k disjoint communities. 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 approximate_maximum_k_cut: 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.
approximate_maximum_k_cut 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 approximate_maximum_k_cut 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 approximate_maximum_k_cut. 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.
approximate_maximum_k_cut 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 →