https://github.com/browserbase/mcp-server-browserbase

Allow LLMs to control a browser with Browserbase and Stagehand
https://github.com/browserbase/mcp-server-browserbase

ai browser chrome chromium mcp playwright puppeteer

Last synced: 25 days ago
JSON representation

Allow LLMs to control a browser with Browserbase and Stagehand

• Host: GitHub
• URL: https://github.com/browserbase/mcp-server-browserbase
• Owner: browserbase
• Created: 2024-12-05T19:20:40.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2025-04-11T00:33:39.000Z (26 days ago)
• Last Synced: 2025-04-11T23:59:53.098Z (25 days ago)
• Topics: ai, browser, chrome, chromium, mcp, playwright, puppeteer
• Language: TypeScript
• Homepage: https://stagehand.dev
• Size: 3.93 MB
• Stars: 776
• Watchers: 11
• Forks: 88
• Open Issues: 18
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-mcp-servers - Browserbase - Cloud-based browser interactions for navigation, data extraction, and form completion (🏢 Enterprise-Supported Implementations / Browser & Web Automation)
• awesome-mcp-servers - Browserbase - Cloud-based browser interactions for navigation, data extraction, and form completion (🏢 Enterprise-Supported Implementations / Browser & Web Automation)
• awesome - browserbase/mcp-server-browserbase - Allow LLMs to control a browser with Browserbase and Stagehand (TypeScript)
• Awesome-MCP-Servers-directory - Browserbase - Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more) (Browser Automation)
• awesome-mcp-servers - Browserbase MCP Server - Allow LLMs to control a browser with Browserbase and Stagehand (Table of Contents / Browser Automation)
• awesome-mcp-servers - Browserbase MCP Server - Allow LLMs to control a browser with Browserbase and Stagehand (Table of Contents / Browser Automation)
• awesome-mcp-servers - Browserbase - Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more) (Official Servers)
• awesome-mcp-zh - browserbase/mcp-server-browserbase
• awesome-mcp-zh - browserbase/mcp-server-browserbase
• awesome-hacking-lists - browserbase/mcp-server-browserbase - Allow LLMs to control a browser with Browserbase and Stagehand (TypeScript)

README

        
# Browserbase MCP Server

![cover](assets/cover-mcp.png)

[The Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) 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](https://www.browserbase.com/), [Puppeteer](https://pptr.dev/), and [Stagehand](https://github.com/browserbase/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](./browserbase/README.md) or [Stagehand MCP](./stagehand/README.md).

## Getting Started with available MCPs

🌐 **Browserbase MCP** - Located in [`browserbase/`](./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/`](./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](https://join.slack.com/t/stagehand-dev/shared_invite/zt-2uvuobu50-~wVSx2Si75CPa3332hwVEw) for support |

### Alternative Installation Methods

[Smithery](https://smithery.ai/server/@browserbasehq/mcp-browserbase)