ai.smithery/browserbasehq-mcp-browserbase MCP Server
ai.smithery/browserbasehq-mcp-browserbase
Cloud browser automation for LLMs, powered by Browserbase and Stagehand.
What is the ai.smithery/browserbasehq-mcp-browserbase MCP server?
The ai.smithery/browserbasehq-mcp-browserbase MCP server is a Model Context Protocol server that gives LLMs cloud browser automation capabilities using Browserbase and Stagehand. It exposes tools to start/end browser sessions, navigate to URLs, act on pages, observe elements, and extract data, allowing AI agents to interact with live web pages programmatically.
This server connects LLM applications to Browserbase's cloud browser infrastructure via Stagehand, enabling web browsing, interaction, and data extraction. It can be used either through Browserbase's hosted SHTTP endpoint (recommended, includes free Gemini model usage) or self-hosted via STDIO (NPM package, local Node install, or Docker). It requires a Browserbase API key and project ID, and supports configuring alternate LLM providers (e.g., GPT-4o, Claude) with their own API keys for driving Stagehand's page understanding and action logic.
How to install ai.smithery/browserbasehq-mcp-browserbase
Copy-paste configuration for popular MCP clients.
AuthorizationrequiredsecretBearer token for Smithery authentication
{
"mcpServers": {
"browserbasehq-mcp-browserbase": {
"url": "https://server.smithery.ai/@browserbasehq/mcp-browserbase/mcp"
}
}
}{
"mcpServers": {
"browserbasehq-mcp-browserbase": {
"serverUrl": "https://server.smithery.ai/@browserbasehq/mcp-browserbase/mcp"
}
}
}{
"servers": {
"browserbasehq-mcp-browserbase": {
"type": "http",
"url": "https://server.smithery.ai/@browserbasehq/mcp-browserbase/mcp"
}
}
}{
"mcpServers": {
"browserbasehq-mcp-browserbase": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://server.smithery.ai/@browserbasehq/mcp-browserbase/mcp"
]
}
}
}claude mcp add --transport http browserbasehq-mcp-browserbase https://server.smithery.ai/@browserbasehq/mcp-browserbase/mcpTools & capabilities
Tools this server exposes to the agent.
start— Create or reuse a Browserbase session.end— Close the current Browserbase session.navigate— Navigate to a URL. Input: { url: string }act— Perform an action on the page. Input: { action: string }observe— Observe actionable elements on the page. Input: { instruction: string }extract— Extract data from the page. Input: { instruction?: string }
Use cases
- Automate web-based tasks (form filling, clicking, navigation) from an LLM agent
- Extract structured data or content from web pages for downstream processing
- Build AI workflows that browse and interact with live websites in the cloud
- Test or observe interactive elements on a webpage before automating actions
- Run browser automation sessions remotely without managing local browser infrastructure
ai.smithery/browserbasehq-mcp-browserbase MCP server FAQ
It gives LLMs cloud browser automation capabilities, letting them start browser sessions, navigate to URLs, perform actions, observe page elements, and extract data using Browserbase and Stagehand.
The server itself is open source under Apache 2.0. The hosted version at mcp.browserbase.com includes Browserbase-provided LLM costs for the default Gemini model, but self-hosting requires your own Browserbase API key, project ID, and optionally your own model API key for custom LLMs.
Add an entry to your MCP config JSON pointing to either the hosted SHTTP endpoint (https://mcp.browserbase.com/mcp) or run it via npx with the @browserbasehq/mcp package (or mcp-remote for clients lacking SHTTP support), supplying BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID as environment variables.
You need a BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID for self-hosted setups. If using a non-default model (not Gemini), you must also supply a modelApiKey for that provider (e.g., Anthropic, OpenAI). The hosted version handles default model costs for you.
Yes, it supports STDIO transport for self-hosting via npx @browserbasehq/mcp, direct git clone with Node, or Docker, though Browserbase recommends the hosted SHTTP version for easiest setup and full capacity.
Yes, use the --modelName flag with a model supported by Stagehand (e.g., anthropic/claude-sonnet-4.5) and provide your own API key via --modelApiKey, since custom models require your own provider credentials.
README (reference)
Source of truth, from the repository.
Browserbase MCP Server

The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you're building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.
This server provides cloud browser automation capabilities using Browserbase and Stagehand. It enables LLMs to interact with web pages, extract information, and perform automated actions.
This is a self-hostable version of the Browserbase hosted MCP server with the same tools and functionality. We recommend using the hosted version for the easiest setup.
Tools
This server exposes 6 tools that match the hosted Browserbase MCP server:
| Tool | Description | Input |
|---|---|---|
start | Create or reuse a Browserbase session | (none) |
end | Close the current Browserbase session | (none) |
navigate | Navigate to a URL | { url: string } |
act | Perform an action on the page | { action: string } |
observe | Observe actionable elements on the page | { instruction: string } |
extract | Extract data from the page | { instruction?: string } |
How to Setup
We currently support 2 transports for our MCP server, STDIO and SHTTP. We recommend you use SHTTP with our hosted MCP server to take advantage of the server at full capacity.
SHTTP (Hosted MCP):
Use the Browserbase hosted MCP server at https://mcp.browserbase.com/mcp. This is the easiest way to get started -- we host the server and provide the LLM costs for Gemini, the best performing model in Stagehand.
For full setup instructions, see the Browserbase MCP documentation.
If your client supports SHTTP:
{
"mcpServers": {
"browserbase": {
"type": "http",
"url": "https://mcp.browserbase.com/mcp"
}
}
}
If your client doesn't support SHTTP:
{
"mcpServers": {
"browserbase": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.browserbase.com/mcp"]
}
}
}
STDIO (Self-Hosted):
You can either use our server hosted on NPM or run it completely locally by cloning this repo.
Note: If you want to use a different model you have to add --modelName to the args and provide that respective key as an arg. More info below.
To run via NPM (Recommended)
Go into your MCP Config JSON and add the Browserbase Server:
{
"mcpServers": {
"browserbase": {
"command": "npx",
"args": ["@browserbasehq/mcp"],
"env": {
"BROWSERBASE_API_KEY": "",
"BROWSERBASE_PROJECT_ID": "",
"GEMINI_API_KEY": ""
}
}
}
}
That's it! Reload your MCP client and you're ready to go.
To run 100% local:
Option 1: Direct installation
git clone https://github.com/browserbase/mcp-server-browserbase.git
cd mcp-server-browserbase
npm install && npm run build
Option 2: Docker
git clone https://github.com/browserbase/mcp-server-browserbase.git
cd mcp-server-browserbase
docker build -t mcp-browserbase .
Then in your MCP Config JSON run the server:
Using Direct Installation
{
"mcpServers": {
"browserbase": {
"command": "node",
"args": ["/path/to/mcp-server-browserbase/cli.js"],
"env": {
"BROWSERBASE_API_KEY": "",
"BROWSERBASE_PROJECT_ID": "",
"GEMINI_API_KEY": ""
}
}
}
}
Using Docker
{
"mcpServers": {
"browserbase": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"BROWSERBASE_API_KEY",
"-e",
"BROWSERBASE_PROJECT_ID",
"-e",
"GEMINI_API_KEY",
"mcp-browserbase"
],
"env": {
"BROWSERBASE_API_KEY": "",
"BROWSERBASE_PROJECT_ID": "",
"GEMINI_API_KEY": ""
}
}
}
}
Configuration
The Browserbase MCP server accepts the following command-line flags:
| Flag | Description |
|---|---|
--proxies | Enable Browserbase proxies for the session |
--verified | Enable Browserbase Verified Identity (Only for Scale Plan Users) |
--advancedStealth | Deprecated alias for --verified |
--keepAlive | Enable Browserbase Keep Alive Session |
--contextId <contextId> | Specify a Browserbase Context ID to use |
--persist | Whether to persist the Browserbase context (default: true) |
--port <port> | Port to listen on for HTTP/SHTTP transport |
--host <host> | Host to bind server to (default: localhost, use 0.0.0.0 for all interfaces) |
--browserWidth <width> | Browser viewport width (default: 1024) |
--browserHeight <height> | Browser viewport height (default: 768) |
--modelName <model> | The model to use for Stagehand (default: google/gemini-2.5-flash-lite) |
--modelApiKey <key> | API key for the custom model provider (required when using custom models) |
--experimental | Enable experimental features (default: false) |
These flags can be passed directly to the CLI or configured in your MCP configuration file.
Note: These flags can only be used with the self-hosted server (npx @browserbasehq/mcp or Docker).
Model Configuration
Stagehand defaults to using Google's Gemini 2.5 Flash Lite model, but you can configure it to use other models like GPT-4o, Claude, or other providers.
Important: When using any custom model (non-default), you must provide your own API key for that model provider using the --modelApiKey flag.
{
"mcpServers": {
"browserbase": {
"command": "npx",
"args": [
"@browserbasehq/mcp",
"--modelName",
"anthropic/claude-sonnet-4.5",
"--modelApiKey",
"your-anthropic-api-key"
],
"env": {
"BROWSERBASE_API_KEY": "",
"BROWSERBASE_PROJECT_ID": ""
}
}
}
}
Note: The model must be supported in Stagehand. Check out the docs here.
Links
License
Licensed under the Apache 2.0 License.
Copyright 2025 Browserbase, Inc.
Related MCP servers
ai.smithery/brave
Give AI agents full Brave Search capabilities: web, local, image, video, news, place search, LLM context, and summarization.
Give AI assistants full control of Unreal Engine—assets, actors, levels, VFX, AI, and cinematics.
AI-powered Unreal Engine control via MCP—automate assets, actors, levels, and effects through native C++ automation.
ai.smithery/docfork-mcp
Up-to-date library documentation for AI coding agents — now shut down (offline since June 14, 2026).
ai.smithery/IlyaGusev-academia_mcp
Search arXiv and ACL Anthology, retrieve citations and references, and browse web sources to accel…
Enable language models to perform advanced AI-powered web scraping with enterprise-grade reliabili…