Estuary

Estuary의 MCP 서버는 AI 어시스턴트(Claude, Cursor, VS Code, ChatGPT)를 Estuary의 실시간 문서에 연결하여, 에디터를 벗어나지 않고도 실시간 및 배치 데이터 파이프라인(CDC, 스트리밍, ETL/ELT) 구축에 관한 정확하고 문서 기반의 답변을 제공합니다.

estuary.dev에서 보기이 MCP 사용해 보기스폰서

호스팅형 MCP 서버

npx add-mcp 'https://estuary.mcp.kapa.ai'

Claude Code, Codex, Cursor 등에 설치됩니다

문서

Skip to main content

On this page

Connect to Estuary's documentation directly from your IDE or AI tool using the Model Context Protocol (MCP).

Overview ​

The Model Context Protocol (MCP) allows AI assistants in your development environment to access Estuary's documentation contextually. This means you can ask questions about Estuary directly in your IDE and get accurate, documentation-backed answers without leaving your workflow.

tip

MCP keeps your assistant's answers accurate. To have it also build and operate pipelines for you, pair it with agent skills. See Using coding agents with Estuary for the full setup.

Setup ​

Server URL: https://estuary.mcp.kapa.ai

Authentication Required

When you first connect to the Estuary MCP server, you'll be prompted to sign in with Google. This is a minimal authentication (OpenID Connect) that doesn't access your email, name, or personal data - it's only used to prevent abuse.

Setup steps vary depending on which AI assistant you're using.

  • Cursor
  • VS Code
  • Claude Code
  • ChatGPT Desktop
  • Claude Desktop
  • Other

Add the following to your .cursor/mcp.json file:

{
  "mcpServers": {
    "estuary": {
      "type": "http",
      "url": "https://estuary.mcp.kapa.ai"
    }
  }
}

For more information, see the Cursor MCP documentation.

Prerequisites: VS Code 1.102+ with GitHub Copilot enabled.

Create an mcp.json file in your workspace .vscode folder:

{
  "servers": {
    "estuary": {
      "type": "http",
      "url": "https://estuary.mcp.kapa.ai"
    }
  }
}

For more details, see the VS Code MCP documentation.

Run the following command in your terminal:

claude mcp add --transport http estuary https://estuary.mcp.kapa.ai

Then run the /mcp command in Claude Code and follow the steps in your browser to authenticate.

For more information, see the Claude Code MCP documentation.

ChatGPT Desktop supports MCP servers in developer mode:

  1. Open ChatGPT Desktop.
  2. Go to Settings > Features.
  3. Enable Developer mode.
  4. Navigate to Settings > MCP Servers.
  5. Click Add Server and enter:
    • Name: estuary
    • URL: https://estuary.mcp.kapa.ai

For more information, see the ChatGPT Desktop MCP documentation.

Add to your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "estuary": {
      "type": "http",
      "url": "https://estuary.mcp.kapa.ai"
    }
  }
}

Restart Claude Desktop for changes to take effect.

For more details, see the Claude Desktop documentation.

MCP is an open protocol supported by many clients. Use the server URL https://estuary.mcp.kapa.ai and refer to your client's documentation for setup instructions.

Most clients accept the standard MCP JSON configuration format:

{
  "mcpServers": {
    "estuary": {
      "url": "https://estuary.mcp.kapa.ai"
    }
  }
}

What you can do ​

Once connected, you can ask context-aware questions about Estuary from within your editor. For example:

  • "How do I set up a PostgreSQL CDC capture?"
  • "What's the difference between captures and materializations?"
  • "How do I create a derivation in TypeScript?"
  • "What connectors are available for data warehouses?"
  • "How do I configure schema evolution settings?"

The AI assistant will use Estuary's documentation to provide accurate, up-to-date answers while you code.

Related pages ​

{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"MCP Integration","item":"https://docs.estuary.dev/features/mcp-integration"}]}