AI agents call triangle_count 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.
Triangle Count is a read-only graph analysis algorithm. It traverses the graph structure to compute a metric (triangle count) for each node but does not modify, delete, or execute code. There are no side effects or irreversible operations.
From the tool's definition Tool description states it 'counts the number of triangles for each node in the graph' — a pure analysis/computation operation with no modification, deletion, or execution of arbitrary code.
Attacks that exploit this kind of access
The Triangle Count algorithm counts the number of triangles for each node 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 triangle_count: 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.
triangle_count 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 triangle_count 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 triangle_count. 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.
triangle_count 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 →