AI agents call label_propagation 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.
Label propagation is a community detection algorithm that analyzes graph structure to classify nodes into communities. This is fundamentally a read operation that retrieves analytical insights from graph data without modifying the underlying database, executing code, or triggering external systems.
From the tool's definition Tool performs label propagation analysis to identify communities in a graph, which is a query/analysis operation. The description indicates it 'finds communities' in a graph using an algorithm that processes existing graph data.
Attacks that exploit this kind of access
The Label Propagation algorithm (LPA) is a fast algorithm for finding communities in a 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 label_propagation: 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.
label_propagation 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 label_propagation 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 label_propagation. 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.
label_propagation 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 →