📌Overview

Purpose: To provide a Model Context Protocol server that enables MCP clients to interact with virtual Ubuntu desktops for various tasks.

Overview: Scrapybara MCP facilitates seamless interactions between MCP clients such as Claude Desktop, Cursor, and Windsurf, and virtual Ubuntu desktops. Users can perform actions including web browsing and code execution, enhancing their productivity in a controlled environment.

Key Features:

start_instance: Initializes a Scrapybara Ubuntu instance, allowing users to access the web or run code within a sandboxed environment while providing a real-time streaming URL for monitoring.
get_instances: Retrieves a list of all currently running Scrapybara instances, making it easy to manage and track active sessions.
stop_instance: Terminates an active Scrapybara instance, providing users with control over their resources.
bash: Executes bash commands within a Scrapybara instance, enabling users to leverage command-line capabilities within the virtual environment.
act: Empowers an agent to perform actions on a Scrapybara instance through user interface interactions and command-line commands, increasing flexibility and utility.

Scrapybara MCP

A Model Context Protocol server for Scrapybara. This server enables MCP clients such as Claude Desktop, Cursor, and Windsurf to interact with virtual Ubuntu desktops and take actions such as browsing the web, running code, and more.

Prerequisites

Node.js 18+
pnpm
Scrapybara API key (get one at https://scrapybara.com)

Installation

Clone the repository:

git clone https://github.com/scrapybara/scrapybara-mcp.git
cd scrapybara-mcp

Install dependencies:

pnpm install

Build the project:

pnpm build

Add the following to your MCP client config:

{
  "mcpServers": {
    "scrapybara-mcp": {
      "command": "node",
      "args": ["path/to/scrapybara-mcp/dist/index.js"],
      "env": {
        "SCRAPYBARA_API_KEY": "<YOUR_SCRAPYBARA_API_KEY>",
        "ACT_MODEL": "<YOUR_ACT_MODEL>", // "anthropic" or "openai"
        "AUTH_STATE_ID": "<YOUR_AUTH_STATE_ID>" // Optional, for authenticating the browser
      }
    }
  }
}

Restart your MCP client.

Tools

start_instance - Start a Scrapybara Ubuntu instance. Use it as a desktop sandbox to access the web or run code. Always present the stream URL to the user afterwards so they can watch the instance in real time.
get_instances - Get all running Scrapybara instances.
stop_instance - Stop a running Scrapybara instance.
bash - Run a bash command in a Scrapybara instance.
act - Take action on a Scrapybara instance through an agent. The agent can control the instance with mouse/keyboard and bash commands.

Contributing

Scrapybara MCP is a community-driven project. Whether you're submitting an idea, fixing a typo, adding a new tool, or improving an existing one, your contributions are greatly appreciated!

Before contributing, read through the existing issues and pull requests to see if someone else is already working on something similar. This helps to avoid duplicating efforts.

If there are more tools or features you'd like to see, feel free to suggest them on the issues page.