capture_ui_screenshot
Capture a screenshot of a URL using headless Playwright. Returns the screenshot as an inline image that multimodal agents can see and evaluate directly. Also captures browser console errors. Supports viewport presets (mobile/tablet/desktop/wide) or custom dimensions. Requires Playwright to be ins...
This record as markdown: /tools/io-github-homenshum-nodebench/capture-ui-screenshot.md
What capture_ui_screenshot does on Nodebench
AI agents invoke capture_ui_screenshot to trigger actions in Nodebench. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why capture_ui_screenshot is rated High
This tool executes a headless browser (Playwright) to navigate to an arbitrary URL and capture screenshots. It triggers external operations (browser automation, network requests to arbitrary URLs) whose effects depend on arguments.
From the tool's definition Capture a screenshot of a URL using headless Playwright... Also captures browser console errors.
Attacks that exploit this kind of access
The rule that runs capture_ui_screenshot 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 capture_ui_screenshot, this is the rule to start with:
capture_ui_screenshot stays usable, but rate-capped: a runaway agent can't fire it dozens of times 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 capture_ui_screenshot call is checked against it from then on.
Questions about capture_ui_screenshot
Capture a screenshot of a URL using headless Playwright. Returns the screenshot as an inline image that multimodal agents can see and evaluate directly. Also captures browser console errors. Supports viewport presets (mobile/tablet/desktop/wide) or custom dimensions. Requires Playwright to be installed in the project. It is categorised as a Execute tool in the Nodebench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nodebench MCP server in PolicyLayer and add a rule for capture_ui_screenshot: 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.
capture_ui_screenshot is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the capture_ui_screenshot 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 capture_ui_screenshot. 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.
capture_ui_screenshot 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.
Across the catalogue