Skip to main content
Glama

puppeteer_screenshot

Capture screenshots of web pages or specific elements using browser automation on Linux display servers. Specify dimensions and CSS selectors for precise captures.

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
widthNoWidth in pixels (default: 800)
heightNoHeight in pixels (default: 600)

Implementation Reference

  • Switch case implementing the puppeteer_screenshot tool: sets viewport, takes screenshot of page or selected element, stores it, and returns image content.
    case "puppeteer_screenshot": {
      const width = args.width ?? 800;
      const height = args.height ?? 600;
      await page.setViewport({ width, height });
      const screenshot = await (args.selector ?
      (await page.$(args.selector))?.screenshot({ encoding: "base64" }) :
      page.screenshot({ encoding: "base64", fullPage: false }));
      if (!screenshot) {
        return {
          content: [{
            type: "text",
            text: args.selector ? `Element not found: ${args.selector}` : "Screenshot failed",
          }],
          isError: true,
        };
      }
      screenshots.set(args.name, screenshot);
      server.notification({
        method: "notifications/resources/list_changed",
      });
      return {
        content: [
          {
            type: "text",
            text: `Screenshot '${args.name}' taken at ${width}x${height}`,
          },
          {
            type: "image",
            data: screenshot,
            mimeType: "image/png",
          },
        ],
        isError: false,
      };
    }
  • Input schema for puppeteer_screenshot tool defining parameters: name (required), selector, width, height.
    {
      name: "puppeteer_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)" },
        },
        required: ["name"],
      },
    },
  • index.ts:447-449 (registration)
    Registration of the tools list via ListToolsRequestSchema handler, which returns the TOOLS array including puppeteer_screenshot.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: TOOLS,
    }));
  • index.ts:451-451 (registration)
    Registration of the CallToolRequestSchema handler, which dispatches to handleToolCall implementing puppeteer_screenshot.
    server.setRequestHandler(CallToolRequestSchema, async (request) => handleToolCall(request.params.name, 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/PhialsBasement/MCP-Puppeteer-Linux'

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