mcp-server-browserbase
Control browsers with LLMs using Browserbase and Stagehand.
- Type
- MCP
- Open source
- Yes
- GitHub Stars
- ★ 3.4k
- Source
- mcp-github
Overview
This MCP server provides cloud browser automation capabilities using Browserbase and Stagehand. It enables LLMs to interact with web pages, extract information, and perform automated tasks. The server supports six tools, including creating/reusing sessions, closing sessions, navigating to URLs, performing page actions, observing actionable elements, and extracting data from pages. It can be accessed via SHTTP or STDIO transport protocols. Ideal for developers looking to integrate browser automation into AI applications.
Capabilities
- ▪Create or reuse a Browserbase session
- ▪Close the current Browserbase session
- ▪Navigate to a specified URL
- ▪Perform page actions
- ▪Observe actionable page elements
- ▪Extract data from a page
Use cases
Setup
Install via NPM: "
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started?
We recommend using the managed version at https://mcp.browserbase.com/mcp.
What transport protocols are supported?
Supports STDIO and SHTTP.
What API keys are required?
Requires BROWSERBASE_API_KEY, BROWSERBASE_PROJECT_ID, and GEMINI_API_KEY.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.