AI agents call dijkstra_single_source_shortest_path 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.
This is a read-only graph algorithm that queries and retrieves computed path information from the Neo4j database. It performs a calculation on existing data without side effects, reversible operations, code execution with external effects, deletions, or financial transactions. The algorithm is deterministic and depends only on graph structure and parameters—a standard analytical query.
From the tool's definition Tool computes and returns shortest paths between nodes without modifying the graph data. Description states it 'computes the shortest path' with no mention of creating, modifying, or deleting data.
Attacks that exploit this kind of access
The Dijkstra Shortest Path algorithm computes the shortest path between 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 dijkstra_single_source_shortest_path: 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.
dijkstra_single_source_shortest_path 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 dijkstra_single_source_shortest_path 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 dijkstra_single_source_shortest_path. 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.
dijkstra_single_source_shortest_path 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 →