AI agents invoke HITS to trigger actions in Neo4j Gds. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The server is designed to execute graph algorithms on Neo4j databases. HITS (Hyperlink-Induced Topic Search) is a well-known graph algorithm for computing hub and authority scores. Given the server's explicit purpose of executing graph algorithms, this tool almost certainly runs the HITS algorithm. Empty description lowers confidence, but the Execute category fits based on server context.
From the tool's definition Tool name is 'HITS' with empty description. Server description states it runs graph algorithms on Neo4j databases by 'selecting and executing appropriate parameterised graph algorithms'.
Attacks that exploit this kind of access
HITS. It is categorised as a Execute tool in the Neo4j Gds MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Neo4j Gds MCP server in PolicyLayer and add a rule for HITS: 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.
HITS is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the HITS 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 HITS. 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.
HITS 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 →