dive_record_test_step
Record the actual result of a test step after executing it via the MCP Bridge. Compare expected vs actual, attach a screenshot, and mark pass/fail. When all steps are recorded, the test is automatically completed with an overall status.
This record as markdown: /tools/io-github-homenshum-nodebench/dive-record-test-step.md
What dive_record_test_step does on Nodebench
AI agents use dive_record_test_step to create or update resources in Nodebench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nodebench environment.
Why dive_record_test_step is rated Medium
This tool records test results, compares expected vs actual outcomes, and updates test step status. It creates/modifies test records (pass/fail, screenshots, results) in a test management system. While it triggers some automated completion logic, the core action is writing structured test result data — reversibly modifiable records — rather than executing arbitrary code or irreversibly destroying data.
From the tool's definition 'Record the actual result of a test step', 'mark pass/fail', 'test is automatically completed with an overall status'
Attacks that exploit this kind of access
The rule that runs dive_record_test_step 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 dive_record_test_step, this is the rule to start with:
dive_record_test_step stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. 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 dive_record_test_step call is checked against it from then on.
Questions about dive_record_test_step
Record the actual result of a test step after executing it via the MCP Bridge. Compare expected vs actual, attach a screenshot, and mark pass/fail. When all steps are recorded, the test is automatically completed with an overall status. It is categorised as a Write tool in the Nodebench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nodebench MCP server in PolicyLayer and add a rule for dive_record_test_step: 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_record_test_step is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the dive_record_test_step 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_record_test_step. 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_record_test_step 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