Whatsapp MCP
A WhatsApp MCP (Model Context Protocol) server that connects your WhatsApp account with AI agents, enabling automated messaging, contact search, and chat interaction through LLMs.
WhatsApp MCP + CLI
A WhatsApp integration that works in two ways:
- MCP Server — lets AI assistants like Claude control WhatsApp directly
- CLI Tool — send/read WhatsApp messages from your terminal
Built on whatsapp-web.js.
Features
- Send WhatsApp messages by contact name or phone number
- Read recent messages from any chat
- List all recent chats with previews
- Search contacts by name
- Works as an MCP server (Claude, etc.) or standalone CLI
Setup
1. Install dependencies
npm install
2. Authenticate WhatsApp
node index.js auth
Scan the QR code with your WhatsApp mobile app. Your session is saved locally — you only need to do this once.
MCP Server (for Claude / AI assistants)
The MCP server exposes 4 tools over stdio:
| Tool | Description |
|---|---|
send_message | Send a message to a contact |
read_messages | Read recent messages from a chat |
list_chats | List recent chats with previews |
search_contacts | Search contacts by name |
Configure in Claude Code
Add to your .mcp.json or Claude Code MCP settings:
{
"mcpServers": {
"whatsapp": {
"command": "node",
"args": ["C:/path/to/whatsapp-cli/mcp-server.mjs"]
}
}
}
Run manually
node mcp-server.mjs
CLI Usage
Send a message
node index.js send --to "John Doe" --message "Hey!"
# or by phone number
node index.js send --to 919876543210 --message "Hey!"
Read messages
node index.js read --from "John Doe" --count 20
List chats
node index.js list-chats --count 10
Use Cases
- AI-powered WhatsApp assistant — plug into Claude or any MCP-compatible AI to read and send messages hands-free
- WhatsApp automation — build bots, auto-responders, or notification systems
- Terminal messaging — send/read WhatsApp messages without opening your phone
- Business notifications — send automated WhatsApp alerts from scripts or cron jobs
Project Structure
├── index.js # CLI entry point
├── mcp-server.mjs # MCP server (for AI assistants)
├── src/
│ ├── client.js # WhatsApp client setup
│ └── commands/
│ ├── auth.js # QR code authentication
│ ├── send.js # Send message command
│ ├── read.js # Read messages command
│ └── list-chats.js # List chats command
└── package.json
Requirements
- Node.js 18+
- A WhatsApp account (personal or business)
License
MIT
相关服务器
AI Interaction Tool
An AI interaction tool with an advanced UI for the Model Context Protocol (MCP).
MCP Email Server
Provides IMAP and SMTP access for sending and receiving emails.
mcp-gmail
MCP server for full Gmail operations via Unipile API. 9 tools: send, reply, list, read, delete, search, labels, attachments, drafts. Dry-run by default, 55 unit tests. MIT licensed.
Pushover MCP
Send push notifications using the Pushover.net service.
Kraiter
Kraiter is an email automation platform. It exposes 62 tools for managing contacts, drip campaigns, transactional sends, segments, templates, domains, and metrics.
WhatsApp
Search, read, and send personal WhatsApp messages, contacts, and media files.
Genesys Cloud MCP Server
Exposes Genesys Cloud tools like sentiment analysis, conversation search, and topic detection for LLMs.
Voice Mode
A server for natural voice conversations with AI assistants like Claude and ChatGPT.
Hawaiihub MCP Server
An MCP server for a Chinese community news platform, featuring automated content collection, multi-platform publishing, and intelligent operations.
SimpleChatJS
A lightweight AI chat application with MCP support, built with pure JavaScript and Node.js.