Browserbase MCP

Browserbase MCP gives AI models actual browser control through cloud infrastructure. Built on Stagehand, it lets you navigate websites, extract data, and interact with web pages using natural language commands.

The integration provides real browser sessions that AI can control, enabling tasks that go beyond simple web search APIs.

Available Tools

Note

Browserbase’s MCP tools evolve over time. This list reflects current capabilities but may change.

Multi-Session Tools

• multi_browserbase_stagehand_session_create: Create parallel browser sessions
• multi_browserbase_stagehand_session_list: Track active sessions
• multi_browserbase_stagehand_session_close: Clean up sessions
• multi_browserbase_stagehand_navigate_session: Navigate in specific session

Core Browser Actions

• browserbase_stagehand_navigate: Navigate to URLs
• browserbase_stagehand_act: Perform actions (“click the login button”)
• browserbase_stagehand_extract: Extract text content
• browserbase_stagehand_observe: Find page elements
• browserbase_screenshot: Capture screenshots

Session Management

• browserbase_session_create: Create or reuse sessions
• browserbase_session_close: Close active sessions

Prerequisites

• Jan with MCP enabled
• Browserbase account (includes 60 minutes free usage)
• Model with strong tool calling support
• Node.js installed

Caution

Currently, only the latest Anthropic models handle multiple tools reliably. Other models may struggle with the full tool set.

Setup

Enable MCP

1. Go to Settings > MCP Servers
2. Toggle Allow All MCP Tool Permission ON

Get Browserbase Credentials

1. Sign up at browserbase.com

   • Email verification required
   • Phone number authentication
   • Thorough security process

2. Access your dashboard and copy:

   • API Key
   • Project ID

Configure MCP Server

Click + in MCP Servers section:

NPM Package Configuration:

• Server Name: browserbase
• Command: npx
• Arguments: @browserbasehq/mcp-server-browserbase
• Environment Variables:
  • Key: BROWSERBASE_API_KEY, Value: your-api-key
  • Key: BROWSERBASE_PROJECT_ID, Value: your-project-id

Verify Setup

Check the tools bubble in chat to confirm Browserbase tools are available:

Real Usage Example

Live Information Query

Which sports matches are happening right now in Australia (irrespective of the sport)?

This simple query demonstrates browser automation in action:

1. Tool Activation
   • Model creates browser session
   • Navigates to sports websites
   • Extracts current match data

2. Results Delivery
   • Real-time match information
   • Multiple sports covered
   • Current scores and timings

The AI successfully found:

• AFL matches with live scores
• NRL games in progress
• Upcoming Rugby Union fixtures

Common Issues

Tool Call Failures

Sometimes tool calls fail due to parsing issues:

Solutions:

• Try rephrasing your prompt
• Disable unnecessary tools
• Use simpler, more direct requests
• Switch to Claude 3.5+ Sonnet if using another model

Model Limitations

Most models struggle with multiple tools. If experiencing issues:

• Start with single-purpose requests
• Build complexity gradually
• Consider which tools are actually needed
• Expect some trial and error initially

Usage Limits

Free Tier:

• 60 minutes of browser time included
• Sessions auto-terminate after 5 minutes inactivity
• Can adjust timeout in Browserbase dashboard
• Usage visible in dashboard analytics

Session Management:

• Each browser session counts against time
• Close sessions when done to conserve minutes
• Multi-session operations consume time faster

Practical Use Cases

Real-Time Data Collection

Check current prices for MacBook Pro M4 at major Australian retailers and create a comparison table.

Form Testing

Navigate to myservice.gov.au and walk through the Medicare claim process, documenting each required field.

Content Monitoring

Visit ABC News Australia and extract the top 5 breaking news headlines with their timestamps.

Multi-Site Analysis

Compare flight prices from Sydney to Tokyo next week across Qantas, Jetstar, and Virgin Australia.

Automated Verification

Check if our company is listed correctly on Google Maps, Yelp, and Yellow Pages, noting any discrepancies.

Advanced Techniques

Session Reuse

Create a browser session, log into LinkedIn, then search for "AI engineers in Melbourne" and extract the first 10 profiles.

Parallel Operations

Create three browser sessions: monitor stock prices on ASX, check crypto on CoinSpot, and track forex on XE simultaneously.

Sequential Workflows

Go to seek.com.au, search for "data scientist" jobs in Sydney, apply filters for $150k+, then extract job titles and companies.

Optimization Tips

Prompt Engineering:

• Be specific about what to extract
• Name exact websites when possible
• Break complex tasks into steps
• Specify output format clearly

Tool Selection:

• Use multi-session only when needed
• Close sessions promptly
• Choose observe before act when possible
• Screenshot sparingly to save time

Error Recovery:

• Have fallback prompts ready
• Start simple, add complexity
• Watch for timeout warnings
• Monitor usage in dashboard

Troubleshooting

Connection Issues:

• Verify API key and Project ID
• Check Browserbase service status
• Ensure NPX can download packages
• Restart Jan after configuration

Browser Failures:

• Some sites block automation
• Try different navigation paths
• Check if site requires login
• Verify target site is accessible

Performance Problems:

• Reduce concurrent sessions
• Simplify extraction requests
• Check remaining time quota
• Consider upgrading plan

Model Struggles:

• Too many tools overwhelm most models
• Claude 3.5+ Sonnet most reliable
• Reduce available tools if needed
• Use focused, clear instructions

Note

Browser automation is complex. Expect occasional failures and be prepared to adjust your approach.

Browserbase vs Browser Use

Feature	Browserbase	Browser Use
Infrastructure	Cloud browsers	Local browser
Setup Complexity	API key only	Python environment
Performance	Consistent	System dependent
Cost	Usage-based	Free (local resources)
Reliability	High	Variable
Privacy	Cloud-based	Fully local

Next Steps

Browserbase MCP provides genuine browser automation capabilities, not just web search. This enables complex workflows like form filling, multi-site monitoring, and data extraction that would be impossible with traditional APIs.

The cloud infrastructure handles browser complexity while Jan maintains conversational privacy. Just remember: with great browser power comes occasional parsing errors.