The Depth First Search algorithm is a graph traversal that starts at a given node and explores as far as possible along each branch before backtracking, see https://en.wikipedia.org/wiki/Depth-first_search.
AI agents call depth_first_search 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.
Depth-first search is a standard graph traversal algorithm that retrieves and analyzes connectivity information in the graph. It has no side effects, does not modify the Neo4j database, and does not execute arbitrary code or trigger external operations. The blast radius of misuse is minimal—an agent could only waste computational resources on expensive traversals, not corrupt or delete data.
From the tool's definition Tool performs 'graph traversal' that 'starts at a given node and explores as far as possible along each branch before backtracking' — a read-only operation that queries graph structure without modifying data.
Attacks that exploit this kind of access
The Depth First Search algorithm is a graph traversal that starts at a given node and explores as far as possible along each branch before backtracking, see https://en.wikipedia.org/wiki/Depth-first_search. 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 depth_first_search: 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.
depth_first_search 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 depth_first_search 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 depth_first_search. 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.
depth_first_search 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 →