traverse_entity_graph
Find all entities and relationships connected to a starting entity within N hops.
This record as markdown: /tools/io-github-homenshum-nodebench/traverse-entity-graph.md
What traverse_entity_graph does on Nodebench
AI agents call traverse_entity_graph to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why traverse_entity_graph is rated Low
This tool retrieves and traverses existing graph data to discover relationships. It has no side effects, does not modify state, execute code, delete data, or trigger financial transactions. It is a read-only query operation analogous to a graph database search or link traversal.
From the tool's definition Tool description states 'Find all entities and relationships' — a pure query/retrieval operation with no data modification, deletion, or code execution. The action is to traverse and return connected graph data.
Attacks that exploit this kind of access
The rule that runs traverse_entity_graph safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For traverse_entity_graph, this is the rule to start with:
traverse_entity_graph is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every traverse_entity_graph call is checked against it from then on.
Questions about traverse_entity_graph
Find all entities and relationships connected to a starting entity within N hops. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for traverse_entity_graph: 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 Nodebench. Nothing to install.
traverse_entity_graph 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 traverse_entity_graph 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 traverse_entity_graph. 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.
traverse_entity_graph is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue