AI agents call article_rank 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 description is empty, so classification relies on the tool name and server context. The sibling tools are all graph algorithms that read and analyze graph data without modifying it. ArticleRank is a well-known variant of PageRank used to measure node importance in graphs. Given the pattern of sibling tools (centrality measures, shortest paths), this is almost certainly a read-only graph analytics operation.
From the tool's definition Tool name 'article_rank' suggests a graph centrality/ranking algorithm similar to PageRank, consistent with sibling tools like betweenness_centrality and closeness_centrality which are read-only analytical operations.
Attacks that exploit this kind of access
article_rank. 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 article_rank: 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.
article_rank 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 article_rank 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 article_rank. 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.
article_rank 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 →