Component Screenshots with Puppeteer MCP

    1

    Capture one component from your local web app as a JPEG after it finishes rendering. Includes a setup guide and a runnable demo.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Component Screenshots with Puppeteer MCP

    Example session with this skill installed

    Open the local URL printed by the included demo. Wait for #build-card[data-state="ready"], capture just #build-card, show the image dimensions, and close the demo tab.

    • Read your context and instructions
    • Compiled the component screenshots

    A 320 × 160 JPEG showing the green card labeled “Build passed” and “12 checks passed”. The page heading is outside the crop. The demo tab is closed after capture.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Give your agent a local preview URL and the component you want to see. The skill waits for the finished state and returns a cropped JPEG with its pixel dimensions.

    The ZIP includes setup instructions, an MCP configuration template, and a demo where the agent waits for a build card to read “Build passed” and captures a 320 × 160 image. Requires Git, Node.js 22.15 or later, npm, and a local MCP client that can display images.

    Requires a local Puppeteer MCP connection. Choose a selector that identifies the finished state of the component. The wait can time out if that state never appears. A very large component can exceed the screenshot size limit.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 10 days ago

    • Free with an Agensi account

    Requires

    Node.js
    puppeteer
    Git

    Permissions

    Browser
    Read Files
    Network Access
    Listed10 days ago

    What's inside

    Frequently Asked Questions

    The skill captures a single element using its CSS selector and returns the JPEG and its dimensions to your agent.

    Use a local agent client that can load the skill, launch a stdio MCP server, and display JPEG results. The capture uses a CSS selector in the rendered page. The setup guide includes a Cursor configuration example.

    Give the agent a selector that appears when the component is ready, such as the ready-state attribute in the demo. It waits for that selector to become visible before capturing the component.

    You get the skill instructions, a setup guide, an MCP configuration template, and a runnable local example. The setup guide links to the browser server and explains how to install it.

    Yes. Give the agent the local preview URL and the component selector. It can reuse a matching tab in the MCP browser or open a new tab for the capture.

    New in Testing & Debugging