Browserbase

Browserbase MCP Server

Allow LLMs to control a browser with Browserbase and Stagehand for AI-powered web automation, intelligent data extraction, and screenshot capture.

What is an MCP Server?⁠

MCP Info

Image Building Info

Attribute	Details
Dockerfile	https://github.com/browserbase/mcp-server-browserbase/blob/main/Dockerfile⁠
Docker Image built by	Docker Inc.
Docker Scout Health Score
Verify Signature	COSIGN_REPOSITORY=mcp/signatures cosign verify mcp/browserbase --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub
Licence	Apache License 2.0

Available Tools (8)

Tools Details

Tool: browserbase_screenshot

Capture a full-page screenshot and return it (and save as a resource).

Tool: browserbase_session_close

Close the current Browserbase session and reset the active context.

Tool: browserbase_session_create

Create or reuse a Browserbase browser session and set it as active.

Tool: browserbase_stagehand_act

Perform a single action on the page (e.g., click, type).

  i.e. 'Click the sign in button' or 'Type 'hello' into the search input'.

variables|objectoptional|Variables used in the action template. ONLY use variables if you're dealing with sensitive data or dynamic content. When using variables, you MUST have the variable key in the action template. ie: {"action": "Fill in the password", "variables": {"password": "123456"}}

Tool: browserbase_stagehand_extract

Extract structured data or text from the current page using an instruction.

Be as detailed and specific as possible about what you want to extract. For example:
'Extract all product names and prices from the listing page'.The more specific your instruction,
the better the extraction results will be.

Tool: browserbase_stagehand_get_url

Return the current page URL (full URL with query/fragment).

Tool: browserbase_stagehand_navigate

Navigate to a URL in the browser. Only use this tool with URLs you're confident will work and be up to date. Otherwise, use https://google.com⁠ as the starting point

Tool: browserbase_stagehand_observe

Find interactive elements on the page from an instruction; optionally return an action.

    This instruction must be extremely specific and descriptive. For example: 'Find the red login button
    in the top right corner', 'Locate the search input field with placeholder text', or 'Identify all
    clickable product cards on the page'. The more specific and detailed your instruction, the better
    the observation results will be. Avoid generic instructions like 'find buttons' or 'see elements'.
    Instead, describe the visual characteristics, location, text content, or functionality of the elements
    you want to observe. This tool is designed to help you identify interactive elements that you can
    later use with the act tool for performing actions like clicking, typing, or form submission.

returnAction|booleanoptional|Whether to return the action to perform on the element. If true, the action will be returned as a string. If false, the action will not be returned.

Use this MCP Server

{
  "mcpServers": {
    "browserbase": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "BROWSERBASE_API_KEY",
        "-e",
        "BROWSERBASE_PROJECT_ID",
        "-e",
        "GEMINI_API_KEY",
        "mcp/browserbase"
      ],
      "env": {
        "BROWSERBASE_API_KEY": "YOUR_BROWSERBASE_API_KEY_HERE",
        "BROWSERBASE_PROJECT_ID": "YOUR_BROWSERBASE_PROJECT_ID_HERE",
        "GEMINI_API_KEY": "YOUR_GEMINI_API_KEY_HERE"
      }
    }
  }
}

Why is it safer to run MCP Servers with Docker?⁠