Selenium MCP Server

Instructions

Implementation Reference

• src/tools/actionTools.ts:484-523 (handler)

  MCP server.tool registration and inline handler for 'browser_screenshot'. Defines input schema, executes screenshot capture via ActionService, and returns either file save confirmation or base64 image data in the tool response.

    'browser_screenshot',
    'Take a screenshot of the current page',
    {
      outputPath: z
        .string()
        .optional()
        .describe('Optional path where to save the screenshot. If not provided, returns base64 data.'),
    },
    async ({ outputPath }) => {
      try {
        const driver = stateManager.getDriver();
        const actionService = new ActionService(driver);
        const screenshot = await actionService.takeScreenshot();
  
        if (outputPath) {
          const fs = await import('fs/promises');
          await fs.writeFile(outputPath, screenshot, 'base64');
          return {
            content: [{ type: 'text', text: `Screenshot saved to ${outputPath}` }],
          };
        } else {
          return {
            content: [
              { type: 'text', text: 'Screenshot captured as base64:' },
              { type: 'text', text: screenshot },
            ],
          };
        }
      } catch (e) {
        return {
          content: [
            {
              type: 'text',
              text: `Error taking screenshot: ${(e as Error).message}`,
            },
          ],
        };
      }
    }
  );

• src/tools/actionTools.ts:486-491 (schema)

  Zod input schema for the browser_screenshot tool: optional outputPath string.

  {
    outputPath: z
      .string()
      .optional()
      .describe('Optional path where to save the screenshot. If not provided, returns base64 data.'),
  },

• src/services/actionService.ts:125-127 (helper)

  Core screenshot capture method in ActionService using Selenium WebDriver's driver.takeScreenshot().

  async takeScreenshot(): Promise<string> {
    return this.driver.takeScreenshot();
  }