We've built an MCP (Model Context Protocol) server for Kadoa. This means you can manage web scraping workflows directly from AI coding assistants like Claude Code, Cursor, Codex, and Gemini CLI.

Instead of switching between the dashboard, docs, and your IDE, you can ask your AI assistant to handle it:

• "Create a workflow to extract product prices from example.com"
• "List my Kadoa workflows"
• "Run workflow abc123 and show me the results"
• "Update the schema for workflow abc123 to include a rating field"

The server exposes eight tools that cover the full workflow lifecycle: create, list, get, run, fetch data, approve, update, and delete.

For Claude Code, one command is all you need:

claude mcp add kadoa -- npx -y @kadoa/mcp

For Claude Desktop, add to your config:

{
  "mcpServers": {
    "kadoa": {
      "command": "npx",
      "args": ["-y", "@kadoa/mcp"],
      "env": {
        "KADOA_API_KEY": "tk-your_api_key"
      }
    }
  }
}

If you have the Kadoa CLI installed, the MCP server picks up your saved API key automatically - no extra configuration needed.

MCP server documentation ->