Skip to main content
Glama
cloudflare

Cloudflare Playwright MCP

Official
by cloudflare

browser_take_screenshot

Read-only

Capture screenshots of web pages or specific elements using Playwright on Cloudflare MCP. Supports PNG or JPEG formats, viewport or full-page capture, and targeted element screenshots for precise web testing.

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

  • Handler function implementing the logic for browser_take_screenshot tool. Captures screenshot of viewport or specific element using Playwright, supports PNG/JPEG, base64 output, and generates execution code.
    handle: async (context, params) => {
      const tab = context.currentTabOrDie();
      const snapshot = tab.snapshotOrDie();
      const fileType = params.raw ? 'png' : 'jpeg';
      const fileName = await outputFile(context.config, params.filename ?? `page-${new Date().toISOString()}.${fileType}`);
      const options: playwright.PageScreenshotOptions = { type: fileType, quality: fileType === 'png' ? undefined : 50, scale: 'css', path: fileName };
      const isElementScreenshot = params.element && params.ref;
    
      const code = [
        `// Screenshot ${isElementScreenshot ? params.element : 'viewport'} and save it as ${fileName}`,
      ];
    
      const locator = params.ref ? snapshot.refLocator({ element: params.element || '', ref: params.ref }) : null;
    
      if (locator)
        code.push(`await page.${await generateLocator(locator)}.screenshot(${javascript.formatObject(options)});`);
      else
        code.push(`await page.screenshot(${javascript.formatObject(options)});`);
    
      const includeBase64 = context.clientSupportsImages();
      const action = async () => {
        const screenshot = locator ? await locator.screenshot(options) : await tab.page.screenshot(options);
        return {
          content: includeBase64 ? [{
            type: 'image' as 'image',
            data: screenshot.toString('base64'),
            mimeType: fileType === 'png' ? 'image/png' : 'image/jpeg',
          }] : []
        };
      };
    
      return {
        code,
        action,
        captureSnapshot: true,
        waitForNetwork: false,
      };
    }
  • Input schema (Zod) for browser_take_screenshot tool parameters: raw, filename, element, ref with validation that element and ref are both provided or neither.
    const screenshotSchema = z.object({
      raw: z.coerce.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.'),
    }).refine(data => {
      return !!data.element === !!data.ref;
    }, {
      message: 'Both element and ref must be provided or neither.',
      path: ['ref', 'element']
    });
  • Definition and initial registration of the browser_take_screenshot tool using defineTool, including metadata like name, title, description, and reference to input schema.
    const screenshot = defineTool({
      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',
      },
  • Export of the defined screenshot tool for use in higher-level tool collections.
    export default [
      screenshot,
    ];
  • src/tools.ts:45-45 (registration)
    Inclusion of the screenshot tool in the snapshotTools array, aggregating tools for registration.
    ...screenshot,
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=true, destructiveHint=false, and openWorldHint=true, covering safety and world state. The description adds valuable context about the tool's limitations ('You can't perform actions based on the screenshot') and clarifies its relationship with browser_snapshot, which goes beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly concise with only two sentences that each serve a distinct purpose: stating the tool's function and providing critical usage guidance. There's zero wasted text and the most important information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the comprehensive annotations (readOnlyHint, destructiveHint, openWorldHint) and 100% schema coverage, the description provides adequate context. It adds the critical limitation about not being able to perform actions based on screenshots, which is important for a screenshot tool. The absence of an output schema is partially compensated by the clear behavioral guidance.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the input schema already fully documents all 5 parameters. The description doesn't add any parameter-specific information beyond what's in the schema, so it meets the baseline expectation without providing additional semantic context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('take a screenshot') and resource ('current page'), and explicitly distinguishes it from sibling tool 'browser_snapshot' by stating 'use browser_snapshot for actions'. This provides clear differentiation from related tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when NOT to use this tool ('You can't perform actions based on the screenshot') and names a specific alternative ('use browser_snapshot for actions'). This gives clear context for tool selection versus alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Related Tools

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/cloudflare/playwright-mcp'

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