Browserless MCP Server

name: browserless-mcp version: 1.0.0 description: Model Context Protocol server for Browserless.io browser automation author: Lizzard Solutions license: MIT repository: https://github.com/Lizzard-Solutions/browserless-mcp keywords: - mcp - browserless - puppeteer - playwright - browser-automation - web-scraping - pdf-generation - screenshots # MCP Server Configuration mcp: name: browserless-mcp version: 1.0.0 description: Comprehensive browser automation through Browserless.io capabilities: tools: {} # Tool definitions tools: - name: initialize_browserless description: Initialize connection to Browserless instance inputSchema: type: object properties: host: type: string default: localhost description: Browserless host address port: type: number default: 3000 description: Browserless port token: type: string description: Authentication token (required) protocol: type: string enum: [http, https, ws, wss] default: http description: Connection protocol timeout: type: number default: 30000 description: Request timeout in milliseconds concurrent: type: number default: 5 description: Maximum concurrent sessions required: [token] - name: generate_pdf description: Generate PDF from URL or HTML content with custom styling inputSchema: type: object properties: url: type: string description: URL to convert to PDF html: type: string description: HTML content to convert to PDF options: type: object properties: displayHeaderFooter: type: boolean description: Display header and footer printBackground: type: boolean description: Print background graphics format: type: string description: Paper format (A4, Letter, etc.) landscape: type: boolean description: Landscape orientation margin: type: object properties: top: type: string description: Top margin (e.g., "20mm") bottom: type: string description: Bottom margin left: type: string description: Left margin right: type: string description: Right margin required: [url] - name: take_screenshot description: Capture screenshots of web pages with various options inputSchema: type: object properties: url: type: string description: URL to screenshot options: type: object properties: type: type: string enum: [png, jpeg, webp] description: Image format quality: type: number description: Image quality (1-100) fullPage: type: boolean description: Capture full page omitBackground: type: boolean description: Omit background clip: type: object properties: x: type: number description: X coordinate y: type: number description: Y coordinate width: type: number description: Width height: type: number description: Height required: [url] - name: get_content description: Extract rendered HTML content after JavaScript execution inputSchema: type: object properties: url: type: string description: URL to extract content from waitForSelector: type: object properties: selector: type: string description: CSS selector to wait for timeout: type: number description: Timeout in milliseconds waitForFunction: type: object properties: fn: type: string description: JavaScript function to wait for timeout: type: number description: Timeout in milliseconds required: [url] - name: execute_function description: Execute custom JavaScript code in browser context inputSchema: type: object properties: code: type: string description: JavaScript code to execute (ES module format) context: type: object properties: {} description: Additional context data required: [code] - name: download_files description: Handle file downloads and programmatic file creation inputSchema: type: object properties: code: type: string description: JavaScript code to trigger downloads context: type: object properties: {} description: Additional context data required: [code] - name: export_page description: Export webpage with all resources inputSchema: type: object properties: url: type: string description: URL to export headers: type: object properties: {} description: Custom headers bestAttempt: type: boolean description: Best effort export required: [url] - name: run_performance_audit description: Run Lighthouse performance audit inputSchema: type: object properties: url: type: string description: URL to audit config: type: object properties: extends: type: string description: Lighthouse config to extend settings: type: object properties: {} description: Lighthouse settings required: [url] - name: unblock description: Bypass bot detection and anti-scraping measures inputSchema: type: object properties: url: type: string description: URL to unblock content: type: boolean description: Return page content screenshot: type: boolean description: Return screenshot stealth: type: boolean description: Enable stealth mode blockAds: type: boolean description: Block advertisements headers: type: object properties: {} description: Custom headers required: [url] - name: execute_browserql description: Execute BrowserQL GraphQL queries for advanced automation inputSchema: type: object properties: query: type: string description: GraphQL query string variables: type: object properties: {} description: Query variables required: [query] - name: create_websocket_connection description: Create WebSocket connection for Puppeteer/Playwright inputSchema: type: object properties: browser: type: string enum: [chromium, firefox, webkit] description: Browser type library: type: string enum: [puppeteer, playwright] description: Automation library stealth: type: boolean description: Enable stealth mode blockAds: type: boolean description: Block advertisements viewport: type: object properties: width: type: number description: Viewport width height: type: number description: Viewport height deviceScaleFactor: type: number description: Device scale factor isMobile: type: boolean description: Mobile emulation hasTouch: type: boolean description: Touch emulation userAgent: type: string description: Custom user agent extraHTTPHeaders: type: object properties: {} description: Additional HTTP headers - name: get_health description: Get health status of Browserless instance inputSchema: type: object properties: {} - name: get_sessions description: Get active browser sessions inputSchema: type: object properties: {} - name: get_config description: Get current configuration inputSchema: type: object properties: {} - name: get_metrics description: Get performance metrics inputSchema: type: object properties: {} # Build Configuration build: entrypoint: dist/index.js dependencies: - "@modelcontextprotocol/sdk" - "puppeteer" - "playwright" - "axios" - "ws" - "zod" - "dotenv" # Documentation documentation: readme: README.md api_reference: ref/browserless_api_reference.md examples: - name: Basic PDF Generation description: Generate PDF from a web page code: | { "name": "generate_pdf", "arguments": { "url": "https://example.com", "options": { "format": "A4", "printBackground": true } } } - name: Screenshot Capture description: Take a full-page screenshot code: | { "name": "take_screenshot", "arguments": { "url": "https://example.com", "options": { "type": "png", "fullPage": true } } } - name: Content Extraction description: Extract content with waiting code: | { "name": "get_content", "arguments": { "url": "https://example.com", "waitForSelector": { "selector": "#content", "timeout": 5000 } } } - name: Custom Function description: Execute custom JavaScript code: | { "name": "execute_function", "arguments": { "code": "export default async function ({ page }) { await page.goto('https://example.com'); const title = await page.title(); return { data: { title }, type: 'application/json' }; }" } } # Metadata metadata: category: Browser Automation tags: - web-scraping - pdf-generation - screenshots - browser-automation - puppeteer - playwright - lighthouse - performance - anti-detection - graphql - websocket features: - PDF generation with custom styling - Screenshot capture (PNG, JPEG, WebP) - Content extraction with JavaScript execution - Custom function execution in browser context - File download handling - Page export with resources - Lighthouse performance audits - Bot detection bypass - BrowserQL GraphQL queries - WebSocket connections for Puppeteer/Playwright - Health monitoring and metrics - Session management use_cases: - Web scraping and data extraction - Automated testing and QA - PDF report generation - Screenshot capture for documentation - Performance monitoring - Content archiving - Form automation - E-commerce monitoring - Social media automation - Compliance reporting # Publishing publish: npm: package_name: "@lizzard-solutions/browserless-mcp" access: public github: repository: Lizzard-Solutions/browserless-mcp releases: true docker: image_name: lizzard-solutions/browserless-mcp platforms: - linux/amd64 - linux/arm64