check_dive_drivers
Setup wizard for MCP automation drivers. Probes the system for Android SDK (ANDROID_HOME, adb, emulator), iOS tools (Xcode, go-ios, simulators), Playwright, and Node.js version. Returns a readiness report with per-area status (ready/partial/missing) and platform-specific setup instructions for Wi...
This record as markdown: /tools/io-github-homenshum-nodebench/check-dive-drivers.md
What check_dive_drivers does on Nodebench
AI agents call check_dive_drivers 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 check_dive_drivers is rated Low
This tool only reads/inspects system configuration and installed tools, returning a diagnostic report. It generates a setup script but does not execute it. No data is modified, deleted, or created — it is purely a system interrogation/read operation.
From the tool's definition Probes the system for Android SDK, iOS tools, Playwright, and Node.js version. Returns a readiness report with per-area status and setup instructions.
Attacks that exploit this kind of access
The rule that runs check_dive_drivers 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 check_dive_drivers, this is the rule to start with:
check_dive_drivers 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 check_dive_drivers call is checked against it from then on.
Questions about check_dive_drivers
Setup wizard for MCP automation drivers. Probes the system for Android SDK (ANDROID_HOME, adb, emulator), iOS tools (Xcode, go-ios, simulators), Playwright, and Node.js version. Returns a readiness report with per-area status (ready/partial/missing) and platform-specific setup instructions for Windows, macOS, or Linux. Also generates a copy-paste setup script. Run this first to see what. 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 check_dive_drivers: 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.
check_dive_drivers 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 check_dive_drivers 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 check_dive_drivers. 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.
check_dive_drivers 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