How to Use H-1B Salary Data in Claude, Cursor, and AI Tools (MCP Server)

You can query 8.5 million H-1B salary records directly from Claude, Cursor, or any MCP-compatible AI tool. The H-1B Salary MCP server connects your AI assistant to real Department of Labor filing data. Setup takes 2 minutes.

MCP (Model Context Protocol) is an open standard created by Anthropic that lets AI tools connect to external data sources. Instead of relying on training data, your AI gets live access to 17 years of H-1B salary filings.

What You Get

The MCP server exposes 3 tools to your AI assistant:

Setup: Claude Desktop

Open your Claude Desktop configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the H-1B salary server:

{
  "mcpServers": {
    "h1b-salaries": {
      "command": "npx",
      "args": ["h1b-salary-mcp"],
      "env": {
        "H1B_API_KEY": "your_api_key_here"
      }
    }
  }
}

Restart Claude Desktop. You will see the H-1B tools appear in the tools menu.

Setup: Cursor

Create .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "h1b-salaries": {
      "command": "npx",
      "args": ["h1b-salary-mcp"],
      "env": {
        "H1B_API_KEY": "your_api_key_here"
      }
    }
  }
}

Setup: Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "h1b-salaries": {
      "command": "npx",
      "args": ["h1b-salary-mcp"],
      "env": {
        "H1B_API_KEY": "your_api_key_here"
      }
    }
  }
}

Setup: VS Code

Create .vscode/mcp.json in your project root:

{
  "servers": {
    "h1b-salaries": {
      "type": "stdio",
      "command": "npx",
      "args": ["h1b-salary-mcp"],
      "env": {
        "H1B_API_KEY": "your_api_key_here"
      }
    }
  }
}

Example Queries

Once connected, ask your AI assistant questions like these:

API Key and Pricing

Get your API key at the API documentation page. The free tier is enough to try the MCP tools and run a few queries per day.

Tips for Best Results

• Be specific with company names: "Google LLC" works better than just "Google"
• Use 2-letter state codes: "CA" not "California"
• Add fiscal_year for the most recent data: fiscal_year 2024
• The get_top_employers tool uses multiple API requests. On the free tier, use it sparingly.
• Use compare_salaries when you need a direct comparison. It is more efficient than running two separate searches.