Skip to main content
Glama

browser_take_screenshot

Capture and save screenshots of web pages or specific elements using Playwright MCP. Supports PNG, JPEG formats, full-page captures, and targeted element screenshots for precise web automation tasks.

Instructions

Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
elementNoHuman-readable element description used to obtain permission to screenshot the element. If not provided, the screenshot will be taken of viewport. If element is provided, ref must be provided too.
filenameNoFile name to save the screenshot to. Defaults to `page-{timestamp}.{png|jpeg}` if not specified.
fullPageNoWhen true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots.
refNoExact target element reference from the page snapshot. If not provided, the screenshot will be taken of viewport. If ref is provided, element must be provided too.
typeNoImage format for the screenshot. Default is png.png

Implementation Reference

  • The main handler function that executes the browser_take_screenshot tool logic, using Playwright to capture screenshot of viewport, full page, or specific element based on parameters, saves to file, adds code comments, and returns image data.
    handle: async (tab, params, response) => { const fileType = params.raw ? 'png' : 'jpeg'; const fileName = await outputFile(tab.context.config, params.filename ?? `page-${new Date().toISOString()}.${fileType}`); const options: playwright.PageScreenshotOptions = { type: fileType, quality: fileType === 'png' ? undefined : 50, scale: 'css', path: fileName, ...(params.fullPage !== undefined && { fullPage: params.fullPage }) }; const isElementScreenshot = params.element && params.ref; const screenshotTarget = isElementScreenshot ? params.element : (params.fullPage ? 'full page' : 'viewport'); response.addCode(`// Screenshot ${screenshotTarget} and save it as ${fileName}`); // Only get snapshot when element screenshot is needed const locator = params.ref ? await tab.refLocator({ element: params.element || '', ref: params.ref }) : null; if (locator) response.addCode(`await page.${await generateLocator(locator)}.screenshot(${javascript.formatObject(options)});`); else response.addCode(`await page.screenshot(${javascript.formatObject(options)});`); const buffer = locator ? await locator.screenshot(options) : await tab.page.screenshot(options); response.addResult(`Took the ${screenshotTarget} screenshot and saved it as ${fileName}`); response.addImage({ contentType: fileType === 'png' ? 'image/png' : 'image/jpeg', data: buffer }); }
  • Zod schema defining input parameters: raw, filename, element, ref, fullPage with validation rules ensuring element and ref are both provided or neither, and fullPage not used with elements.
    const screenshotSchema = z.object({ raw: z.boolean().optional().describe('Whether to return without compression (in PNG format). Default is false, which returns a JPEG image.'), filename: z.string().optional().describe('File name to save the screenshot to. Defaults to `page-{timestamp}.{png|jpeg}` if not specified.'), element: z.string().optional().describe('Human-readable element description used to obtain permission to screenshot the element. If not provided, the screenshot will be taken of viewport. If element is provided, ref must be provided too.'), ref: z.string().optional().describe('Exact target element reference from the page snapshot. If not provided, the screenshot will be taken of viewport. If ref is provided, element must be provided too.'), fullPage: z.boolean().optional().describe('When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots.'), }).refine(data => { return !!data.element === !!data.ref; }, { message: 'Both element and ref must be provided or neither.', path: ['ref', 'element'] }).refine(data => { return !(data.fullPage && (data.element || data.ref)); }, { message: 'fullPage cannot be used with element screenshots.', path: ['fullPage'] });
  • Tool definition and registration using defineTabTool, specifying name 'browser_take_screenshot', metadata, input schema, and handler function.
    const screenshot = defineTabTool({ capability: 'core', schema: { name: 'browser_take_screenshot', title: 'Take a screenshot', description: `Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.`, inputSchema: screenshotSchema, type: 'readOnly', }, handle: async (tab, params, response) => { const fileType = params.raw ? 'png' : 'jpeg'; const fileName = await outputFile(tab.context.config, params.filename ?? `page-${new Date().toISOString()}.${fileType}`); const options: playwright.PageScreenshotOptions = { type: fileType, quality: fileType === 'png' ? undefined : 50, scale: 'css', path: fileName, ...(params.fullPage !== undefined && { fullPage: params.fullPage }) }; const isElementScreenshot = params.element && params.ref; const screenshotTarget = isElementScreenshot ? params.element : (params.fullPage ? 'full page' : 'viewport'); response.addCode(`// Screenshot ${screenshotTarget} and save it as ${fileName}`); // Only get snapshot when element screenshot is needed const locator = params.ref ? await tab.refLocator({ element: params.element || '', ref: params.ref }) : null; if (locator) response.addCode(`await page.${await generateLocator(locator)}.screenshot(${javascript.formatObject(options)});`); else response.addCode(`await page.screenshot(${javascript.formatObject(options)});`); const buffer = locator ? await locator.screenshot(options) : await tab.page.screenshot(options); response.addResult(`Took the ${screenshotTarget} screenshot and saved it as ${fileName}`); response.addImage({ contentType: fileType === 'png' ? 'image/png' : 'image/jpeg', data: buffer }); } });

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nzjami/mcpPlaywright'

If you have feedback or need assistance with the MCP directory API, please join our Discord server