AI agents call articulation_points 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 queries the graph to detect articulation points (nodes whose removal would disconnect the graph). It performs a read-only algorithmic analysis with no side effects, data modification, or execution of arbitrary code. The blast radius if misused is minimal since it only reads graph structure.
From the tool's definition 'Find all the articulation points' — this is a read-only graph analysis operation that identifies nodes meeting a structural criterion without modifying any data.
Attacks that exploit this kind of access
Find all the articulation points. Given a graph, an articulation point is a node whose removal increases the number of connected components in 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 articulation_points: 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.
articulation_points 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 articulation_points 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 articulation_points. 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.
articulation_points 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 →