Happy slice of mcp pizzaMCP.pizza
Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AIFire in da houseCheck it out free

mcp-server-browserbase

MCP.Pizza Chef: browserbase

The mcp-server-browserbase is an MCP server that empowers large language models (LLMs) to control and automate cloud browsers using Browserbase and Stagehand technologies. It allows LLMs to interact with web pages dynamically, execute JavaScript, and capture screenshots within a cloud browser environment. This server is ideal for integrating real-time web navigation, data extraction, and browser automation into AI-powered applications, chat interfaces, and custom workflows. By standardizing browser control through MCP, it facilitates seamless, secure, and observable interactions between LLMs and web content, enhancing AI capabilities across platforms.

Use This MCP server To

Automate web page interactions in a cloud browser Capture screenshots of web pages for analysis Execute JavaScript on web pages remotely Enable LLM-driven web navigation and scraping Integrate browser automation into AI workflows Support real-time web data extraction for LLMs

README

Browserbase MCP Server

cover

The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you’re building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

This server provides cloud browser automation capabilities using Browserbase and Stagehand. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a cloud browser environment.

To learn to get started with Browserbase, check out Browserbase MCP or Stagehand MCP.

Getting Started with available MCPs

🌐 Browserbase MCP - Located in browserbase/

Feature Description
Browser Automation Control and orchestrate cloud browsers
Data Extraction Extract structured data from any webpage
Console Monitoring Track and analyze browser console logs
Screenshots Capture full-page and element screenshots
Web Interaction Navigate, click, and fill forms with ease

🤘 Stagehand MCP - Located in stagehand/

Feature Description
Atomic Instructions Execute precise actions like act("click the login button") or extract("find the red shoes")
Model Flexibility Supports multiple models, including OpenAI's GPT-4 and Anthropic's Claude-3.7 Sonnet
Modular Design Easily integrate new models with minimal changes
Vision Support Use annotated screenshots for complex DOMs
Open Source Contribute to the project and join the Slack community for support

Alternative Installation Methods

Smithery

Credits

Huge thanks and shoutout to the Playwright team for their contributions to the framework, and their work on the Playwright MCP Server

mcp-server-browserbase FAQ

How do I install the mcp-server-browserbase?
You can install it by cloning the GitHub repository and following the setup instructions in the Browserbase MCP README, which includes dependencies for Browserbase and Stagehand.
Can this server execute JavaScript on any web page?
Yes, the server allows LLMs to run JavaScript within the cloud browser environment on supported web pages, enabling dynamic interaction and data retrieval.
Is the browser automation environment cloud-based or local?
The mcp-server-browserbase operates in a cloud browser environment, leveraging Browserbase's cloud infrastructure for scalable and remote browser control.
How does this server ensure secure interaction with web pages?
It uses scoped and observable model interactions defined by MCP principles, ensuring that LLMs operate within controlled permissions and secure contexts.
Can I use this server with different LLM providers?
Yes, it is provider-agnostic and works with various LLMs including OpenAI, Anthropic Claude, and Google Gemini, as long as they support MCP integration.
What kind of web interactions can LLMs perform using this server?
LLMs can navigate pages, click elements, fill forms, execute scripts, and capture screenshots, enabling comprehensive browser automation.
Are there any limitations on the types of websites this server can interact with?
Interaction depends on the website's compatibility with Browserbase and Stagehand; some sites with advanced bot protections may limit automation capabilities.
How do I get started with development using this MCP server?
Start by reviewing the Browserbase MCP and Stagehand MCP documentation in the repository, which provide examples and API references for integration.