nodebench_query_elements
Query all agent-annotated interactive elements on the current page. Returns elements with their data-agent-id, action type, label, and target. Use this to understand what you can interact with on the current view.
This record as markdown: /tools/io-github-homenshum-nodebench/nodebench-query-elements.md
What nodebench_query_elements does on Nodebench
AI agents call nodebench_query_elements 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 nodebench_query_elements is rated Low
This tool retrieves and queries information about interactive elements on a page (their IDs, action types, labels, and targets) without modifying, executing actions, or causing side effects. It is purely informational—analogous to inspecting the DOM or listing available UI components. The description explicitly states it is for understanding the view, not interacting with it.
From the tool's definition Query all agent-annotated interactive elements on the current page. Returns elements with their data-agent-id, action type, label, and target. Use this to understand what you can interact with on the current view.
Attacks that exploit this kind of access
The rule that runs nodebench_query_elements 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 nodebench_query_elements, this is the rule to start with:
nodebench_query_elements 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 nodebench_query_elements call is checked against it from then on.
Questions about nodebench_query_elements
Query all agent-annotated interactive elements on the current page. Returns elements with their data-agent-id, action type, label, and target. Use this to understand what you can interact with on the current view. 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 nodebench_query_elements: 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.
nodebench_query_elements 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 nodebench_query_elements 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 nodebench_query_elements. 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.
nodebench_query_elements 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