Skip to main content
Glama

playwright_screenshot

Capture screenshots of web pages or specific elements using CSS selectors. Save as PNG or base64 format, customize dimensions, and specify download directories with Playwright MCP Server.

Instructions

Take a screenshot of the current page or a specific element

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
downloadsDirNoCustom downloads directory path (default: user's Downloads folder)
heightNoHeight in pixels (default: 600)
nameYesName for the screenshot
savePngNoSave screenshot as PNG file (default: false)
selectorNoCSS selector for element to screenshot
storeBase64NoStore screenshot in base64 format (default: true)
widthNoWidth in pixels (default: 800)

Implementation Reference

  • Main execution logic for the playwright_screenshot tool. Captures screenshot of page or element, optionally saves as PNG file and/or stores base64 image as a server resource.
    case "playwright_screenshot": {
      try {
        const screenshotOptions: any = {
          type: args.type || "png",
          fullPage: !!args.fullPage
        };
    
        if (args.selector) {
          const element = await page!.$(args.selector);
          if (!element) {
            return {
              toolResult: {
                content: [{
                  type: "text",
                  text: `Element not found: ${args.selector}`,
                }],
                isError: true,
              },
            };
          }
          screenshotOptions.element = element;
        }
    
        if (args.mask) {
          screenshotOptions.mask = await Promise.all(
            args.mask.map(async (selector: string) => await page!.$(selector))
          );
        }
    
        const screenshot = await page!.screenshot(screenshotOptions);
        const base64Screenshot = screenshot.toString('base64');
    
        const responseContent: (TextContent | ImageContent)[] = [];
    
        // Handle PNG file saving
        if (args.savePng !== false) {
          const timestamp = new Date().toISOString().replace(/[:.]/g, '-');
          const filename = `${args.name}-${timestamp}.png`;
          const downloadsDir = args.downloadsDir || defaultDownloadsPath;
    
          // Create downloads directory if it doesn't exist
          if (!fs.existsSync(downloadsDir)) {
            fs.mkdirSync(downloadsDir, { recursive: true });
          }
    
          const filePath = path.join(downloadsDir, filename);
          await fs.promises.writeFile(filePath, screenshot);
          responseContent.push({
            type: "text",
            text: `Screenshot saved to: ${filePath}`,
          } as TextContent);
        }
    
        // Handle base64 storage
        if (args.storeBase64 !== false) {
          screenshots.set(args.name, base64Screenshot);
          server.notification({
            method: "notifications/resources/list_changed",
          });
    
          responseContent.push({
            type: "image",
            data: base64Screenshot,
            mimeType: "image/png",
          } as ImageContent);
        }
    
        return {
          toolResult: {
            content: responseContent,
            isError: false,
          },
        };
      } catch (error) {
        return {
          toolResult: {
            content: [{
              type: "text",
              text: `Screenshot failed: ${(error as Error).message}`,
            }],
            isError: true,
          },
        };
      }
    }
  • Tool schema definition including name, description, and input schema with properties for screenshot options.
    {
      name: "playwright_screenshot",
      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" },
          width: { type: "number", description: "Width in pixels (default: 800)" },
          height: { type: "number", description: "Height in pixels (default: 600)" },
          storeBase64: { type: "boolean", description: "Store screenshot in base64 format (default: true)" },
          savePng: { type: "boolean", description: "Save screenshot as PNG file (default: false)" },
          downloadsDir: { type: "string", description: "Custom downloads directory path (default: user's Downloads folder)" },
        },
        required: ["name"],
      },
    },
  • Registration of the listTools request handler which returns the array of all tools including playwright_screenshot schema.
    // List tools handler
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: tools,
    }));
  • Registration of the callTool request handler which routes tool calls to handleToolCall including for playwright_screenshot.
    // Call tool handler
    server.setRequestHandler(CallToolRequestSchema, async (request) =>
      handleToolCall(request.params.name, request.params.arguments ?? {}, server)
    );
  • Helper constant listing tools that require a browser instance, used to conditionally launch Chromium before executing playwright_screenshot.
    export const BROWSER_TOOLS = [
      "playwright_navigate",
      "playwright_screenshot",
      "playwright_click",
      "playwright_fill",
      "playwright_select",
      "playwright_hover",
      "playwright_evaluate"
    ];
Behavior2/5

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

No annotations are provided, so the description carries full burden. It states the action but lacks critical behavioral details: it doesn't mention if this requires a page to be loaded, what happens on failure (e.g., invalid selector), whether it's synchronous or asynchronous, or any performance/rate limits. For a tool with 7 parameters and no annotation coverage, this is a significant gap.

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 a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded and wastes no space, making it easy to parse quickly.

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

Completeness2/5

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

Given the tool's complexity (7 parameters, no output schema, and no annotations), the description is insufficient. It lacks context on prerequisites (e.g., needing an active browser session), output behavior (what is returned—file path, base64 data?), error handling, and interaction with sibling tools, leaving significant gaps for an AI agent.

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?

Schema description coverage is 100%, providing clear documentation for all 7 parameters, so the description adds no additional parameter semantics. The baseline score of 3 reflects adequate coverage by the schema alone, with the description not compensating but not detracting either.

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

Purpose4/5

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

The description clearly states the action ('Take a screenshot') and target ('current page or a specific element'), which is specific and unambiguous. However, it doesn't differentiate from sibling tools like playwright_get or playwright_evaluate that might also involve page interactions, missing explicit distinction.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. With siblings like playwright_get (which might retrieve page content) or playwright_evaluate (which might execute scripts), there's no indication of scenarios where screenshotting is preferred over other methods for capturing page state.

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/lebrodus/mcp-playwright'

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