AI agents call degree_centrality 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.
Centrality algorithms are analytical functions that query and compute properties of existing graph structures. They retrieve and process data to answer graph-related questions, producing analysis results without creating, modifying, or deleting data. No side effects on the database.
From the tool's definition Tool name 'degree_centrality' indicates a graph algorithm that computes node centrality metrics. Sibling tools (a_star_shortest_path, betweenness_centrality, articulation_points, etc.) are all read-only graph analysis algorithms that extract metrics from…
Attacks that exploit this kind of access
degree_centrality. 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 degree_centrality: 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.
degree_centrality 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 degree_centrality 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 degree_centrality. 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.
degree_centrality 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 →