puppeteer-mcp-server-ws
MCP ServerFreeExperimental MCP server for browser automation using Puppeteer (inspired by @modelcontextprotocol/server-puppeteer)
Capabilities8 decomposed
websocket-based browser automation via mcp protocol
Medium confidenceExposes Puppeteer browser automation capabilities as an MCP (Model Context Protocol) server over WebSocket connections, allowing LLM clients to control headless Chrome/Chromium instances through standardized tool-calling interfaces. Implements the MCP server specification to translate tool invocations into Puppeteer API calls, managing browser lifecycle and session state across multiple concurrent client connections.
Bridges Puppeteer and MCP protocol via WebSocket, enabling LLM agents to invoke browser automation as standardized tools without custom API development. Uses MCP's tool-calling schema to map Puppeteer methods into discoverable, type-safe operations for language models.
Lighter-weight than building a custom REST API wrapper around Puppeteer; integrates directly with MCP-aware LLM clients (Claude, etc.) without intermediate HTTP layers, reducing complexity for agent developers.
headless browser page navigation and content retrieval
Medium confidenceProvides tools to navigate to URLs, wait for page load conditions, and retrieve page content (HTML, text, screenshots) via Puppeteer's page automation API. Implements timeout-based wait strategies (waitForNavigation, waitForSelector) to handle dynamic content loading and AJAX-driven pages, returning structured page state to the LLM client.
Exposes Puppeteer's page navigation and content APIs through MCP tool interface, allowing LLMs to declaratively specify wait conditions (e.g., 'wait for selector .results-container') rather than managing async/await patterns directly.
More reliable than simple HTTP GET requests for JavaScript-heavy sites; integrates wait-for-load logic natively, whereas headless browser alternatives (Selenium, Playwright) require separate orchestration layers when exposed via MCP.
dom element interaction and form automation
Medium confidenceEnables clicking, typing, and form submission on page elements via CSS selectors or XPath queries. Implements Puppeteer's type(), click(), and evaluate() methods to interact with DOM elements, with built-in error handling for missing selectors and stale element references. Supports keyboard shortcuts, file uploads, and multi-step form workflows.
Wraps Puppeteer's low-level DOM interaction methods (click, type, evaluate) as MCP tools, allowing LLMs to compose multi-step form workflows declaratively without managing browser state or async control flow.
More direct than Selenium's WebDriver protocol for LLM integration; MCP tool interface abstracts away browser session management, making it easier for agents to chain interactions without boilerplate.
dom query and data extraction via javascript evaluation
Medium confidenceExecutes arbitrary JavaScript in the page context to query and extract structured data from the DOM. Uses Puppeteer's page.evaluate() to run functions in the browser's JavaScript runtime, returning JSON-serializable results. Supports complex queries (e.g., 'extract all product listings as JSON') without requiring the LLM to parse raw HTML.
Exposes Puppeteer's page.evaluate() as an MCP tool, enabling LLMs to write inline JavaScript for complex data extraction without context-switching to a separate scripting environment. Results are automatically JSON-serialized for LLM consumption.
More flexible than CSS selector-based extraction for complex queries; allows LLMs to express extraction logic in JavaScript directly, reducing the need for post-processing in the agent's reasoning loop.
multi-page session management and context switching
Medium confidenceManages multiple browser pages/tabs within a single browser context, allowing LLM agents to switch between pages, maintain separate session states, and coordinate interactions across multiple URLs. Implements page pooling and lifecycle management to track open pages and clean up resources. Supports isolated cookies and local storage per context.
Tracks multiple Puppeteer pages as distinct MCP tool contexts, allowing LLMs to reference and switch between pages by ID without managing browser internals. Abstracts page lifecycle as a stateful service.
Simpler than managing multiple browser instances; keeps session state (cookies, auth) unified while allowing page-level isolation, reducing complexity for agents coordinating multi-page workflows.
network request/response interception and monitoring
Medium confidenceIntercepts and logs HTTP requests and responses made by the page, enabling inspection of API calls, network timing, and response payloads. Uses Puppeteer's request interception API to capture network events, optionally blocking or modifying requests. Useful for debugging, extracting API responses, and understanding page behavior.
Exposes Puppeteer's request interception as MCP tools, allowing LLMs to inspect and filter network traffic without writing custom event listeners. Captures API responses for direct extraction without parsing HTML.
More direct than parsing HTML for API-driven sites; intercepts network calls at the browser level, giving agents access to structured API responses before JavaScript rendering.
browser performance and metrics collection
Medium confidenceCollects performance metrics (page load time, Core Web Vitals, memory usage, CPU) from the browser using Puppeteer's metrics API and Chrome DevTools Protocol. Provides timing breakdowns (DNS, TCP, TLS, TTFB, DOM interactive) and resource usage statistics for performance analysis and optimization.
Exposes Chrome DevTools Protocol metrics through MCP tools, giving LLMs direct access to browser performance data without requiring separate monitoring infrastructure. Metrics are structured and queryable.
More comprehensive than simple timing measurements; provides Core Web Vitals and resource breakdowns that are difficult to extract from HTTP headers alone.
cookie and local storage management
Medium confidenceManages browser cookies and local storage for session persistence and authentication. Allows setting, getting, and clearing cookies/storage across pages in a context. Supports cookie attributes (domain, path, expiry, secure, httpOnly) for fine-grained control. Useful for maintaining login sessions and testing authentication flows.
Exposes Puppeteer's cookie and storage APIs as MCP tools, allowing LLMs to manage authentication state declaratively without handling browser internals. Supports full cookie attribute specification.
More flexible than HTTP-only cookie handling; allows LLMs to inspect and manipulate browser storage directly, enabling complex session management workflows.
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with puppeteer-mcp-server-ws, ranked by overlap. Discovered automatically through the match graph.
Puppeteer
** - Browser automation and web scraping.
puppeteer-mcp-server
Experimental MCP server for browser automation using Puppeteer (inspired by @modelcontextprotocol/server-puppeteer)
puppeteer-mcp-server
Experimental MCP server for browser automation using Puppeteer (inspired by @modelcontextprotocol/server-puppeteer)
@hisma/server-puppeteer
Fork and update (v0.6.5) of the original @modelcontextprotocol/server-puppeteer MCP server for browser automation using Puppeteer.
@todoforai/puppeteer-mcp-server
Experimental MCP server for browser automation using Puppeteer (inspired by @modelcontextprotocol/server-puppeteer)
WebScraping.AI
** - Interact with **[WebScraping.AI](https://WebScraping.AI)** for web data extraction and scraping.
Best For
- ✓AI agent developers building web scraping or form-filling workflows
- ✓Teams deploying LLM-driven RPA (Robotic Process Automation) solutions
- ✓Researchers prototyping browser-based task automation with language models
- ✓Web scraping workflows where pages require JavaScript rendering
- ✓LLM-driven research tasks that need to fetch and analyze live web content
- ✓Accessibility testing or visual regression detection in automated workflows
- ✓RPA workflows automating data entry and form submission
- ✓Testing web applications with complex interactive flows
Known Limitations
- ⚠Experimental/unstable — not production-hardened; API surface may change without notice
- ⚠No built-in session persistence — browser state is lost if server restarts
- ⚠WebSocket overhead adds latency compared to direct Puppeteer library usage; suitable for remote access but not ultra-low-latency scenarios
- ⚠Single-threaded event loop may bottleneck under high concurrent automation load (100+ simultaneous browser operations)
- ⚠No built-in JavaScript execution sandbox — arbitrary page scripts run with full browser privileges
- ⚠Screenshot capture is memory-intensive for large pages; base64 encoding adds ~33% overhead to response size
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
Package Details
About
Experimental MCP server for browser automation using Puppeteer (inspired by @modelcontextprotocol/server-puppeteer)
Categories
Alternatives to puppeteer-mcp-server-ws
Are you the builder of puppeteer-mcp-server-ws?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →