Data MCP Server

🚀 Data MCP Server

This is the Model Context Protocol (MCP) server for Data. It offers various tools for scraping, extracting structured data, and crawling web pages. It also provides an easy way to access general browser agents, such as OpenAI's CUA, Anthropic's Claude Computer Use, and Browser Use.

More information about Data can be found here. The Data API supports a superset of all the features in the MCP server.

More information about the Model Context Protocol can be found here.

🚀 Quick Start

✨ Features

• Data Extraction: Extract formatted content from web pages and convert messy HTML into structured JSON.
• Web Crawling: Navigate multiple related pages and extract formatted content suitable for LLMs.
• Search and Automation: Use Bing for web searches and perform browser automation tasks.
• Profile Management: Create, delete, and list persistent Data profiles.

📦 Installation

Manual Installation

To install the server, run:

npx data-mcp <YOUR-DATA-API-KEY>

Running on Cursor

Add the following to ~/.cursor/mcp.json as shown below:

{
  "mcpServers": {
    "data": {
      "command": "npx",
      "args": ["-y", "data-mcp"],
      "env": {
        "DATA_API_KEY": "YOUR-API-KEY"
      }
    }
  }
}

Running on Windsurf

Add the following to your ./codeium/windsurf/model_config.json as shown below:

{
  "mcpServers": {
    "data": {
      "command": "npx",
      "args": ["-y", "data-mcp"],
      "env": {
        "DATA_API_KEY": "YOUR-API-KEY"
      }
    }
  }
}

Development

For development purposes, you can run the server directly from the source code.

1. Clone the repository:

git clone git@github.com:NexusX-MCP/data-mcp-server.git data-mcp
cd data-mcp

2. Install dependencies:

npm install # or yarn install
npm run build

3. Run the server:

node dist/server.js

Claude Desktop Application

Here is an example configuration for the Data MCP server for the Claude desktop client.

{
  "mcpServers": {
    "data": {
      "command": "npx",
      "args": ["--yes", "data-mcp"],
      "env": {
        "DATA_API_KEY": "your-api-key"
      }
    }
  }
}

💻 Usage Examples

Tools

• scrape_webpage - Extract formatted content (Markdown, screenshots, etc.) from any web page.
• crawl_webpages - Navigate multiple related pages and extract formatted content suitable for LLMs.
• extract_structured_data - Convert messy HTML into structured JSON.
• search_with_bing - Query the web using Bing search.
• browser_use_agent - Fast, lightweight browser automation using a browser use agent.
• openai_computer_use_agent - Perform general automation using OpenAI's CUA model.
• claude_computer_use_agent - Handle complex browser tasks using Claude Computer Use.
• create_profile - Create a new persistent Data profile.
• delete_profile - Delete an existing persistent Data profile.
• list_profiles - List all existing persistent Data profiles.

Installation via Smithery

To automatically install for the Claude desktop application via Smithery, run:

smithery install data-mcp --key <YOUR-DATA-API-KEY>

📚 Documentation

Configuration

Environment Variables

To set the API key in the server, you can use the environment variable DATA_API_KEY. For example, add the following to the .env file:

DATA_API_KEY=your-api-key

Then run:

npx data-mcp

📄 License

This project is licensed under the MIT License.