Skip to main content
Glama

browser_screenshot

Capture web page screenshots or specific elements using CSS selectors for documentation, testing, or visual verification in browser automation workflows.

Instructions

Take a screenshot of the current page or a specific element

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesName for the screenshot
selectorNoCSS selector for element to screenshot
fullPageNoTake a full page screenshot (default: false)

Implementation Reference

  • Handler function for the 'browser_screenshot' tool. Captures screenshot of page or element using Playwright, converts to base64, stores it, notifies resource change, and returns success message with image content.
    case ToolName.BrowserScreenshot: { const fullPage = (args.fullPage === 'true'); const screenshot = await (args.selector ? page.locator(args.selector).screenshot() : page.screenshot({ fullPage })); const base64Screenshot = screenshot.toString('base64'); if (!base64Screenshot) { return { content: [{ type: "text", text: args.selector ? `Element not found: ${args.selector}` : "Screenshot failed", }], isError: true, }; } screenshots.set(args.name, base64Screenshot); server.notification({ method: "notifications/resources/list_changed", }); return { content: [ { type: "text", text: `Screenshot '${args.name}' taken`, } as TextContent, { type: "image", data: base64Screenshot, mimeType: "image/png", } as ImageContent, ], isError: false, }; }
  • index.ts:48-60 (registration)
    Tool registration object for 'browser_screenshot' added to the TOOLS array, which is served via ListToolsRequestSchema. Includes name, description, and input schema.
    { name: ToolName.BrowserScreenshot, description: "Take a screenshot of the current page or a specific element", inputSchema: { type: "object", properties: { name: { type: "string", description: "Name for the screenshot" }, selector: { type: "string", description: "CSS selector for element to screenshot" }, fullPage: { type: "boolean", description: "Take a full page screenshot (default: false)", default: false }, }, required: ["name"], }, },
  • Input schema defining parameters for browser_screenshot: name (required), selector (optional), fullPage (optional boolean).
    inputSchema: { type: "object", properties: { name: { type: "string", description: "Name for the screenshot" }, selector: { type: "string", description: "CSS selector for element to screenshot" }, fullPage: { type: "boolean", description: "Take a full page screenshot (default: false)", default: false }, }, required: ["name"], },
  • Enum definition mapping ToolName.BrowserScreenshot to the string 'browser_screenshot' used throughout the code.
    BrowserScreenshot = "browser_screenshot",
  • index.ts:640-646 (registration)
    MCP server request handlers for listing tools (via TOOLS array) and calling tools (routes to handleToolCall switch).
    server.setRequestHandler(ListToolsRequestSchema, async () => ({ tools: TOOLS, })); server.setRequestHandler(CallToolRequestSchema, async (request) => handleToolCall(request.params.name as ToolName, request.params.arguments ?? {}) );

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/Automata-Labs-team/MCP-Server-Playwright'

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