Skip to content

mcp-browserbase-js

Directory actions

More options

Directory actions

More options

Latest commit

 

History

History

mcp-browserbase-js

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
README.md
README.md
 
 
env.template
env.template
 
 
index.ts
index.ts
 
 
package-lock.json
package-lock.json
 
 
package.json
package.json
 
 

README.md

Browserbase MCP Example

This example demonstrates how to use the Browserbase MCP server with E2B to create a web automation agent that can take screenshots and interact with web pages.

Features

  • Connect to Browserbase MCP server through E2B
  • Use OpenAI Agents to automate web tasks
  • Take screenshots of web pages
  • Stream results in real-time

Prerequisites

  • E2B API key
  • Browserbase API key
  • Browserbase project ID
  • Gemini API key (for Browserbase)
  • OpenAI API key

Setup

  1. Copy the environment template:

    cp env.template .env

  2. Fill in your API keys in the .env file:

    E2B_API_KEY=your_e2b_api_key
BROWSERBASE_API_KEY=your_browserbase_api_key
BROWSERBASE_PROJECT_ID=your_browserbase_project_id
GEMINI_API_KEY=your_gemini_api_key
OPENAI_API_KEY=your_openai_api_key

  3. Install dependencies:

    npm install

  4. Run the example:

    npm start

What it does

The example creates an E2B sandbox with the Browserbase MCP server, connects an OpenAI Agent to it, and then asks the agent to take a screenshot of the E2B landing page and describe what it's about.

Learn more