Define and track a structured interaction test for a component. Provide preconditions and a sequence of test steps (action, target, expected outcome). The agent executes each step via the MCP Bridge (browser_click, browser_type, etc.), takes screenshots, and records actual results here. Each step...
Part of the Nodebench server.
Free to start. No card required.
AI agents call dive_interaction_test to retrieve information from Nodebench without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though dive_interaction_test only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"dive_interaction_test": {}
}
}See the full Nodebench policy for all 724 tools.
These attack patterns abuse exactly the kind of access dive_interaction_test gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Define and track a structured interaction test for a component. Provide preconditions and a sequence of test steps (action, target, expected outcome). The agent executes each step via the MCP Bridge (browser_click, browser_type, etc.), takes screenshots, and records actual results here. Each step gets pass/fail status. The test aggregates into an overall result. This creates the detailed walkthrough with preconditions, steps, expected vs actual, and visual evidence at each step.. 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 dive_interaction_test: 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.
dive_interaction_test 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 dive_interaction_test 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 dive_interaction_test. 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.
dive_interaction_test 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.
Deterministic rules across all 724 Nodebench tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.