Skip to main content
Glama

browser_take_screenshot

Capture screenshots of web pages or specific elements using specified formats (png, jpeg) and save with custom filenames. Supports full-page or viewport-specific captures for precise documentation or analysis.

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 handler function that implements the core logic of taking a screenshot of the viewport, full page, or specific element using Playwright APIs, saving it to a file, generating code snippets, and adding the image to the response.
    handle: async (tab, params, response) => { const fileType = params.type || 'png'; const fileName = await tab.context.outputFile(params.filename ?? `page-${new Date().toISOString()}.${fileType}`); const options: playwright.PageScreenshotOptions = { type: fileType, quality: fileType === 'png' ? undefined : 90, 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 the input parameters for the tool, including validations for element/ref pairing and fullPage compatibility.
    const screenshotSchema = z.object({ type: z.enum(['png', 'jpeg']).default('png').describe('Image format for the screenshot. Default is png.'), 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'] });
  • Defines the tool using defineTabTool, specifying capability, schema (including name 'browser_take_screenshot'), and handler, then exports it as default array for aggregation.
    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.type || 'png'; const fileName = await tab.context.outputFile(params.filename ?? `page-${new Date().toISOString()}.${fileType}`); const options: playwright.PageScreenshotOptions = { type: fileType, quality: fileType === 'png' ? undefined : 90, 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 }); } });
  • src/tools.ts:36-52 (registration)
    Aggregates tools from all tool modules, including screenshot, into the allTools array used by filteredTools.
    export const allTools: Tool<any>[] = [ ...common, ...console, ...dialogs, ...evaluate, ...files, ...install, ...keyboard, ...navigate, ...network, ...mouse, ...pdf, ...screenshot, ...snapshot, ...tabs, ...wait, ];
  • In BrowserServerBackend constructor, sets this._tools to filteredTools(config), which includes the screenshot tool; tools() exposes schemas to MCP server, callTool invokes handlers.
    constructor(config: FullConfig, factories: FactoryList) { this._config = config; this._browserContextFactory = factories[0]; this._tools = filteredTools(config); if (factories.length > 1) this._tools.push(this._defineContextSwitchTool(factories));

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/maywzh/playwright-mcp'

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