AI agents call yens_shortest_paths 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.
Yen's k-shortest paths algorithm is a classic graph query algorithm that retrieves path data from the graph without modifying it. The tool description is minimal, but the algorithm name and context (sibling tools are all analytical/read operations on a Neo4j graph) strongly suggest this is a read-only graph analytics operation. Severity is low since it only queries graph data.
From the tool's definition 'yens_shortest_paths' — Yen's algorithm computes k-shortest paths in a graph, a read-only graph traversal/query operation.
Attacks that exploit this kind of access
Yen. 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 yens_shortest_paths: 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.
yens_shortest_paths 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 yens_shortest_paths 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 yens_shortest_paths. 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.
yens_shortest_paths 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 →