random_walk

Random Walk is an algorithm that provides random paths in a graph.

Server Neo4j Gds neo4j-contrib/gds-agent
Category Read
Risk class Low
Parameters 00 required

What random_walk does on Neo4j Gds

AI agents call random_walk 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.

Why random_walk needs a policy

The tool traverses the graph to produce random paths, which is a read-only operation. It queries existing graph topology and returns path information without creating, modifying, or deleting any data. Consistent with other read-only graph algorithms on this server (BFS, shortest path, centrality measures).

From the tool's definition 'Random Walk is an algorithm that provides random paths in a graph' — it reads graph structure to generate paths without modifying data.

Questions about random_walk

What does the random_walk tool do? +

Random Walk is an algorithm that provides random paths in a graph. It is categorised as a Read tool in the Neo4j Gds MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on random_walk? +

Register the Neo4j Gds MCP server in PolicyLayer and add a rule for random_walk: 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.

What risk level is random_walk? +

random_walk is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit random_walk? +

Yes. Add a rate_limit block to the random_walk 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.

How do I block random_walk completely? +

Set action: deny in the PolicyLayer policy for random_walk. 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.

What MCP server provides random_walk? +

random_walk 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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.