AI agents call leiden 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.
The Leiden algorithm performs community detection by analyzing graph topology. It reads graph data and returns community assignments without creating, modifying, or deleting any data. As with other graph analytics algorithms on this server, it executes a parameterized algorithm on the Neo4j GDS (Graph Data Science) library, which operates on projected in-memory graphs rather than modifying the underlying database.
From the tool's definition 'detecting communities in large networks' — purely analytical, read-only graph algorithm that identifies community structure without modifying data
Attacks that exploit this kind of access
The Leiden algorithm is an algorithm for detecting communities in large networks. 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 leiden: 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.
leiden 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 leiden 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 leiden. 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.
leiden 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 →