AI agents call k_core_decomposition 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.
K-core decomposition is a standard graph algorithm that computes decomposition layers of the graph for analytical purposes. It queries and analyzes graph structure but does not create, modify, delete, or execute external operations. The operation is deterministic and has no side effects on the underlying graph data, making it a Read operation with low risk.
From the tool's definition The tool performs k-core decomposition, which 'separates the nodes in a graph into groups' by analyzing 'degree sequence and topology'. This is a read-only graph analysis operation that retrieves structural information without modifying data.
Attacks that exploit this kind of access
The K-core decomposition constitutes a process of separates the nodes in a graph into groups based on the degree sequence and topology of the graph. 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 k_core_decomposition: 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.
k_core_decomposition 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 k_core_decomposition 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 k_core_decomposition. 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.
k_core_decomposition 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 →