AI agents call all_pairs_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.
APSP computes and returns path information without modifying any data. It reads graph topology and weights to calculate shortest paths. Severity is medium because running this on a large graph could be computationally expensive and potentially cause performance issues on the database, but there are no write or destructive side effects.
From the tool's definition 'calculates the shortest (weighted) path between all pairs of nodes' — purely a read/query operation on graph data
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The All Pairs Shortest Path (APSP) calculates the shortest (weighted) path between all pairs of nodes. 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 all_pairs_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.
all_pairs_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 all_pairs_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 all_pairs_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.
all_pairs_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 →