home / mcp / browsercat mcp server

BrowserCat MCP Server

Provides cloud-based browser automation for LLMs to interact with web pages, capture screenshots, and execute JavaScript in a real browser.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "browsercat-browsercat-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@browsercatco/mcp-server"
      ],
      "env": {
        "BROWSERCAT_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

BrowserCat MCP Server enables LLMs to control a real browser in the cloud, allowing you to navigate web pages, take screenshots, interact with elements, fill forms, and run JavaScript without installing browsers locally.

How to use

You interact with the BrowserCat MCP Server through an MCP client to perform common web automation tasks in a cloud browser. Use the provided tools to navigate to URLs, capture screenshots, click or hover elements, fill forms, select dropdown options, and evaluate JavaScript in the browser console. All actions run in BrowserCat’s cloud environment and you receive browser logs and screenshots as outputs.

How to install

Prerequisites: you need Node.js and npm installed on your machine.

Install and run the BrowserCat MCP Server client-side harness using the following steps.

# Install Node.js from https://nodejs.org (includes npm)

# Run the BrowserCat MCP Server using npx as shown in the runtime example
BROWSERCAT_API_KEY=your-api-key-here npx -y @browsercatco/mcp-server

Additional content

Environment variable you must provide is BROWSERCAT_API_KEY. This key authenticates your requests with the BrowserCat cloud service.

Example configuration to run the MCP server locally with the required API key:

{
  "mcpServers": {
    "browsercat": {
      "command": "npx",
      "args": ["-y", "@browsercatco/mcp-server"],
      "env": {
        "BROWSERCAT_API_KEY": "your-api-key-here"
      }
    }
  }
}

Available tools

browsercat_navigate

Navigate to a URL in the cloud browser. Input: url (string)

browsercat_screenshot

Capture screenshots of the full page or a specific element. Inputs: name (string, required), selector (string), width (number, default 800), height (number, default 600)

browsercat_click

Click an element on the page. Input: selector (string)

browsercat_hover

Hover over an element on the page. Input: selector (string)

browsercat_fill

Fill out form fields. Inputs: selector (string), value (string)

browsercat_select

Select an option from a dropdown. Inputs: selector (string), value

browsercat_evaluate

Execute JavaScript in the browser console. Input: script (string)