AI agents call max_flow 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.
Max flow is a graph algorithm that computes and reports the maximum flow value between source and target nodes given capacity constraints. It reads the graph topology and relationship capacities, runs a computation, and returns a result. There is no indication it modifies, deletes, or writes data back to the database, nor does it execute arbitrary code or move money.
From the tool's definition the max-flow algorithm assigns a flow to each relationship to achieve maximal transport from source to target — this is a graph computation/analysis operation
Attacks that exploit this kind of access
Given source nodes, target nodes and relationships with capacity constraints, the max-flow algorithm assigns a flow to each relationship to achieve maximal transport from source to target. 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 max_flow: 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.
max_flow 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 max_flow 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 max_flow. 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.
max_flow 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 →