Browserbase Extension

This tutorial covers how to add the Browserbase MCP Server as a goose extension for browser automation, enabling programmatic control over navigation, page interactions, and content capture.

TLDR

goose Desktop

Launch the installer

goose CLI

Command

npx @browserbasehq/mcp

Environment Variables

BROWSERBASE_PROJECT_ID: <YOUR_PROJECT_ID>
BROWSERBASE_API_KEY: <YOUR_API_KEY>

Configuration

info

Note that you'll need Node.js installed on your system to run this command, as it uses npx.

goose Desktop

1. Launch the installer
2. Click Yes to confirm the installation
3. Get your Browserbase credentials and paste it in
4. Click Add Extension
5. Click the button in the top-left to open the sidebar
6. Navigate to the chat

goose CLI

1. Run the configure command:

goose configure

2. Choose to add a Command-line Extension.

┌   goose-configure 
│
◇  What would you like to configure?
│  Add Extension 
│
◆  What type of extension would you like to add?
│  ○ Built-in Extension
│  ● Command-line Extension (Run a local command or script)
│  ○ Remote Extension (SSE)
│  ○ Remote Extension (Streaming HTTP)
└

3. Give your extension a name.

┌   goose-configure 
│
◇  What would you like to configure?
│  Add Extension
│
◇  What type of extension would you like to add?
│  Command-line Extension
│
◆  What would you like to call this extension?
│  Browserbase
└

4. Enter the command to run when this extension is used.

┌   goose-configure 
│
◇  What would you like to configure?
│  Add Extension
│
◇  What type of extension would you like to add?
│  Command-line Extension 
│
◇  What would you like to call this extension?
│  Browserbase
│
◆  What command should be run?
│  npx @browserbasehq/mcp
└

5. Enter the number of seconds Goose should wait for actions to complete before timing out. Default is 300 seconds.

┌   goose-configure 
│
◇  What would you like to configure?
│  Add Extension
│
◇  What type of extension would you like to add?
│  Command-line Extension
│
◇  What would you like to call this extension?
│  Browserbase
│
◇  What command should be run?
│  npx @browserbasehq/mcp
│
◆  Please set the timeout for this tool (in secs):
│  300
└

6. Enter a description for this extension.

┌   goose-configure 
│
◇  What would you like to configure?
│  Add Extension
│
◇  What type of extension would you like to add?
│  Command-line Extension
│
◇  What would you like to call this extension?
│  Browserbase
│
◇  What command should be run?
│  npx @browserbasehq/mcp
│
◇  Please set the timeout for this tool (in secs):
│  300
│
◆  Enter a description for this extension:
│  Automate web browsing and data extraction
└

7. Add environment variables for this extension.

info

Obtain your Browserbase credentials and paste them in.

┌   goose-configure 
│
◇  What would you like to configure?
│  Add Extension
│
◇  What type of extension would you like to add?
│  Command-line Extension
│
◇  What would you like to call this extension?
│  Browserbase
│
◇  What command should be run?
│  npx @browserbasehq/mcp
│
◇  Please set the timeout for this tool (in secs):
│  300
│
◇  Enter a description for this extension:
│  Automate web browsing and data extraction
│
◆  Would you like to add environment variables?
│  Yes
│
◇  Environment variable name:
│  BROWSERBASE_PROJECT_ID
│
◇  Environment variable value:
│  ▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪
│
◇  Add another environment variable?
│  Yes
│
◇  Environment variable name:
│  BROWSERBASE_API_KEY
│
◇  Environment variable value:
│  ▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪
│
◇  Add another environment variable?
│  No
│
└  Added Browserbase extension

Example Usage

Let's use the Browserbase extension to gather information about trending MCP-related repositories on GitHub.

LLM

Claude 4 Sonnet was used for this task.

goose Prompt

1. Go to https://github.com/trending

2. Search for "MCP server" or scroll through and find repos with "MCP" or "Model Context Protocol" in the title or description

3. For the top 3 relevant repositories:
    • Click into the repo
    • Take a screenshot of the repo page
    • Extract:
        - Repo name
        - Description
        - Stars today
        - First paragraph of README 
    • Navigate back

- Close all tabs

- Output a Markdown report showing:
    • Repo name (link)
    • Screenshot
    • Description + Stars
    • README excerpt

goose Output

# MCP Repositories Report

## 1. [FastMCP](https://github.com/jlowin/fastmcp)

![FastMCP Repository Screenshot]

**Description**: The fast, Pythonic way to build MCP servers and clients.  
**Stars Today**: 10.2k stars

**README Excerpt**: The Model Context Protocol (MCP) is a new, standardized way to provide context and tools to your LLMs, and FastMCP makes building MCP servers and clients simple and intuitive. Create tools, expose resources, define prompts, and connect components with clean, Pythonic code.

## 2. [GitHub MCP Server](https://github.com/github/github-mcp-server)

![GitHub MCP Server Screenshot]

**Description**: GitHub's official MCP Server that provides seamless integration with GitHub APIs, enabling advanced automation and interaction capabilities for developers and tools.  
**Stars Today**: 13.9k stars

**README Excerpt**: The GitHub MCP Server is a Model Context Protocol (MCP) server that provides seamless integration with GitHub APIs, enabling advanced automation and interaction capabilities for developers and tools.

## 3. [Playwright MCP](https://github.com/microsoft/playwright-mcp)

![Playwright MCP Screenshot]

**Description**: A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright.  
**Stars Today**: 10.2k stars

**README Excerpt**: A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.