이것은 TypeScript를 내장하고 @whiskeysockets/baileys 라이브러리를 사용하여 WhatsApp에 모델 Context Protocol (MCP) 서버입니다.

개인 WhatsApp 계정을 AI 에이전트 (Anthropic Claude와 같은 데스크톱 앱 또는 Cursor)에 연결할 수 있습니다.

• 개인 WhatsApp 메시지 검색.
• 연락처 검색 (개인, 그룹이 아닙니다).
• 최근 채팅 목록.
• 특정 채팅에 대한 메시지를 검색합니다.
• 개인 또는 그룹에 메시지 보내기.

그것은 WhatsApp 웹 멀티 장치 API를 사용하여 ** 개인 WhatsApp 계정**에 직접 연결됩니다. 모든 메시지 및 인증 세부 사항은 SQLite 데이터베이스 (./data/) 및 인증 캐시 (./auth_info/)에 **로 저장됩니다. 데이터는 명시적으로 제공 된 MCP 도구를 사용하여 연결된 AI 에이전트로 전송됩니다 (이제의 인터페이스를 통해 제어).

• (선택 사항 : 스크린 샷 또는 GIF를 여기에 참조 예와 유사한 고려) *

예

사용자: whatsapp 메시지 보내기 “Meu amor” whatsapp 말하기 “Te amo”

---

참가자: 먼저 연락해야 합니다. 사용 도구: whatsapp.search_contacts

---

** 공구 결과:**

---

참가자:

WhatsApp MCP Server (TypeScript/Baileys)

This is a Model Context Protocol (MCP) server for WhatsApp, built with TypeScript and using the @whiskeysockets/baileys library.

It allows you to connect your personal WhatsApp account to an AI agent (like Anthropic Claude via its desktop app or Cursor) enabling it to:

• Search your personal WhatsApp messages.
• Search your contacts (individuals, not groups).
• List your recent chats.
• Retrieve message history for specific chats.
• Send messages to individuals or groups.

It connects directly to your personal WhatsApp account using the WhatsApp Web multi-device API. All your messages and authentication details are stored locally in a SQLite database (./data/) and authentication cache (./auth_info/). Data is only sent to the connected AI agent when it explicitly uses the provided MCP tools (which you control via the agent’s interface).

(Optional: Consider adding a screenshot or GIF similar to the reference example here)

Example

User: Send a whatsapp message to “Meu amor” in whatsapp saying “Te amo”

---

Assistant: Okay, I need to find the contact first. Using tool: whatsapp.search_contacts

{
  "query": "Meu amor"
}

---

Tool Result:

[
  {
    "jid": "[email protected]",
    "name": "Meu Amor"
  }
]

---

Assistant: Found the contact. Now sending the message. Using tool: whatsapp.send_message

{
  "recipient": "[email protected]",
  "message": "Te amo"
}

---

Tool Result:

Message sent successfully to [email protected] (ID: XXXXXXXXXXX).

Key Features (MCP Tools)

The server exposes the following tools to the connected AI agent:

• search_contacts: Search for contacts by name or phone number part (JID).
• list_messages: Retrieve message history for a specific chat, with pagination.
• list_chats: List your chats, sortable by activity or name, filterable, paginated, optionally includes last message details.
• get_chat: Get detailed information about a specific chat.
• get_message_context: Retrieve messages sent immediately before and after a specific message ID for context.
• send_message: Send a text message to a specified recipient JID (user or group).

Installation

Installing via Smithery

To install WhatsApp MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @jlucaso1/whatsapp-mcp-ts --client claude

Prerequisites

• Node.js: Version 23.10.0 or higher (as specified in package.json). You can check your version with node -v. (Has initial typescript and sqlite builtin support)
• npm (or yarn/pnpm): Usually comes with Node.js.