MCP server
Browserbase MCP server
Browserbase's hosted MCP server gives AI a cloud browser that can browse, act on pages, observe elements and extract data.
- Official server
- Browser automation
At a glance
- Maintained by
- Browserbase
- Tools exposed
- 6 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
Running browsers for AI agents at scale is hard: they need memory, they get blocked and they must be isolated from each other. Browserbase runs browsers in the cloud for you, and its MCP server lets an assistant start a session, open pages, act on a page in plain language, observe elements and extract data.
The act, observe and extract tools let the assistant work at a higher level than individual clicks, such as "click the login button" or "extract the table of prices".
The GitHub repository has been archived, and Browserbase now supports the hosted server as the main path. The API key is passed in the server address, so treat that address as a secret. Sessions run in Browserbase's cloud, which keeps browsing away from your own network.
Usage is billed by Browserbase. We end sessions as soon as a task finishes and set limits on how long an agent may browse.
Use cases
Best business use cases
Scale browsing
Data extraction
Portal tasks
Remote testing
Network isolation
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read and write: drives a cloud browser that can read pages, click and fill forms.
-
startCreate or reuse a Browserbase session.
-
endClose the current Browserbase session.
-
navigateGo to a URL.
-
actPerform an action on the page described in plain language.
-
observeFind actionable elements on the page.
-
extractExtract data from the page.
Workflows
Example workflows
Extract a price table
-
1
Start a cloud session.
-
2
Go to the product page.
-
3
Ask the assistant to extract the price table.
-
4
Review the structured result.
-
5
End the session.
Log into a partner portal safely
-
1
Store credentials in a secure vault, not in the prompt.
-
2
Start a session and open the portal.
-
3
Act on the login form with approved credentials.
-
4
Extract the needed report.
-
5
End the session and clear it.
Prompts
Example prompts
“Open this page and extract the pricing table as JSON.”
“Go to the partner portal and download last month's statement.”
“Observe this page and list all the buttons and links.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"browserbase": {
"command": "npx",
"args": [
"@browserbasehq/mcp"
],
"env": {
"BROWSERBASE_API_KEY": "",
"BROWSERBASE_PROJECT_ID": "",
"GEMINI_API_KEY": ""
}
}
}
}Claude Code: terminal
claude mcp add --transport http browserbase "https://mcp.browserbase.com/mcp?browserbaseApiKey=YOUR_BROWSERBASE_API_KEY"- Hosted server: streamable-http; https://mcp.browserbase.com/mcp; API key as query parameter browserbaseApiKey.
- Local server: stdio; @browserbasehq/mcp.
- Needs: BROWSERBASE_API_KEY; BROWSERBASE_PROJECT_ID (local, per README); GEMINI_API_KEY (local, default Stagehand model).
Security
Security considerations
-
Secret server address
The API key is in the address. Keep it private.
-
End sessions
Close sessions when tasks finish.
-
Untrusted pages
Treat page content as data, not instructions.
-
Review actions
Approve actions that submit data.
Related servers
Servers that pair well with it
Playwright
Microsoft's Playwright MCP server lets AI drive a real browser: open pages, read them, click, type, fill forms and take screenshots.
Apify
Apify's official MCP server lets AI find and run ready-made scrapers and automation tools, called Actors, and read their results.
Firecrawl
Firecrawl's official MCP server lets AI scrape, map, crawl and search the web and get clean, AI-ready content back.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- AI agents AI that takes actions in your systems, such as qualifying leads or processing requests, with people checking the results.
- Ecommerce websites Online stores with clean product catalogs, simple checkout and the integrations that keep orders moving.
- Website speed optimization Find what makes a site slow and fix it, so pages load quickly on phones and rank better in search.
- CRM integration Connect your CRM to forms, email, billing and support so customer records stay complete without typing.
Solutions
View all solutions- Price monitoring Collect competitor prices automatically, match them to your products and alert you when something changes.
- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- AI lead qualification Score, research and route every new inquiry so your team talks to the best leads first.
- Email triage Sort a shared inbox by topic and urgency, pull out the key details and draft replies for a person to send.
Industries
View all industriesGuides and articles
View all guides and articles- What are AI agents and how do businesses use them? What AI agents are, real business uses, the controls they need and how to start with one safely.
- What is the Model Context Protocol? A business guide to MCP: what it is, how MCP servers work, who supports it and how to start using it.
- How to build an AI workflow with MCP servers Plan, connect and test an AI workflow that uses MCP servers, from a single task to a reliable process.
- AI chatbot vs AI agent What separates a chatbot that answers from an agent that acts, and when you need each.
AI models
View all ai models- Claude Fable 5.1 The top tier of the Claude family, for the most demanding reasoning and long-horizon agent work, priced above Opus.
- Claude Opus 5.5 Anthropic's recommended starting point for most serious work: long-running agentic coding and knowledge work, with a 1M token context window.
- GPT-6 Astra OpenAI's most capable model, built for the hardest end-to-end work: complex reasoning, coding, computer use and research.
- DeepSeek V4 Pro DeepSeek's model for demanding reasoning and agent work, with thinking effort levels, tool calling, JSON output and a 1 million token window.
- Grok 4.7 xAI's current flagship for coding, agent tasks and knowledge work, with image input, tool calling, structured outputs, reasoning effort levels and a 500K window.
- Reasoning Models that think through multi-step problems before answering: analysis, planning, math, complex documents and agent work.
Glossary terms
View all glossary terms- AI agent An AI agent is software that uses a language model to plan steps, call tools and act toward a goal, instead of only answering one question.
- API integration An API integration connects two or more systems through their APIs so data and actions flow between them automatically.
- Model Context Protocol The Model Context Protocol, or MCP, is an open standard for connecting AI assistants to external tools and data in a consistent way.
- MCP server An MCP server is a program or hosted service that exposes a system's data and actions as tools that AI assistants can use through the Model Context Protocol.
- Tool calling Tool calling is when an AI model asks the application to run a tool, such as a search or database lookup, and then uses the result in its answer.
- CRM A CRM, or customer relationship management system, stores contacts, companies, deals and interactions so a team can manage its customer relationships in one place.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
The GitHub repository is archived. Browserbase supports the hosted server.
In Browserbase's cloud, not on your computer.
As a parameter in the hosted server address, so keep that address private.