mcp-server-browserbase
by: browserbase
Allow LLMs to control a browser with Browserbase and Stagehand
📌Overview
Purpose: The Browserbase MCP Server aims to facilitate seamless integration between LLM applications and web tools by providing cloud browser automation capabilities.
Overview: The Model Context Protocol (MCP) is designed for smooth interactions between large language models (LLMs) and external data sources. This server leverages Browserbase, Puppeteer, and Stagehand to enable LLMs to operate within a cloud browser environment, allowing them to automate tasks such as web navigation and data extraction.
Key Features:
-
Browser Automation: Control and orchestrate cloud browsers to enhance LLM capabilities in real-time interactions.
-
Data Extraction: Extract structured data efficiently from any website, empowering applications with relevant and up-to-date information.
-
Console Monitoring: Track and analyze browser console logs to ensure smooth operation and debug issues effectively.
-
Screenshots: Capture full-page and element-specific screenshots for better context in LLM operations.
-
JavaScript Execution: Run custom JavaScript within the browser context, enabling advanced interactions and modifications.
-
Web Interaction: Navigate, click, and fill forms effortlessly, allowing for dynamic and responsive user experiences.
Browserbase MCP Server
The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools, providing a standardized way to connect LLMs with the context they need.
This server offers cloud browser automation capabilities using Browserbase, Puppeteer, and Stagehand. It allows LLMs to interact with web pages, take screenshots, and execute JavaScript in a cloud browser environment.
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 |
| JavaScript | Execute custom JS in the browser context |
| 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 |