Skip to main content

​
Claude Desktop Setup

Use the remote HTTP MCP endpoint with a lightweight proxy: 
https://mcp.scrapegraphai.com/mcp
Add to your Claude config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS): 
{
  "mcpServers": {
    "scrapegraph-mcp": {
      "command": "npx",
      "args": [
        "[email protected]",
        "https://mcp.scrapegraphai.com/mcp",
        "--header",
        "X-API-Key:YOUR_API_KEY"
      ]
    }
  }
}

​
Local (stdio) alternative

Install and run locally: 
pip install scrapegraph-mcp
export SGAI_API_KEY=your-api-key
Config (~/Library/Application Support/Claude/claude_desktop_config.json): 
{
  "mcpServers": {
    "scrapegraph-mcp-local": {
      "command": "python3",
      "args": ["-m", "scrapegraph_mcp.server"],
      "env": { "SGAI_API_KEY": "YOUR_API_KEY" }
    }
  }
}

​
Alternative: use the CLI directly

{
  "mcpServers": {
    "scrapegraph-mcp": {
      "command": "scrapegraph-mcp",
      "env": { "SGAI_API_KEY": "YOUR_API_KEY" }
    }
  }
}

​
Windows tip

If setting environment variables is problematic on Windows: 
cmd /c "set SGAI_API_KEY=YOUR_API_KEY && python -m scrapegraph_mcp.server"
  • Make sure the CLI is on your PATH (might be in ~/.local/bin or the venv).
  • You can provide an absolute python path if needed (pyenv/venv).
  • Use python3 on macOS if python points to Python 2.

​
Optional: Smithery

npx -y @smithery/cli install @ScrapeGraphAI/scrapegraph-mcp --client claude
Prefer the Remote HTTP method above unless you specifically need Smithery provisioning.