whatsapp-mcp

WhatsApp MCP server that allows AI to read and send WhatsApp messages.

MCPOfficeOpen source

Type: MCP
Transport: stdio
Open source: Yes
GitHub Stars: ★ 5.8k
Source: mcp-github
Repository: github.com/lharries/whatsapp-mcp

Overview

The WhatsApp MCP server is a Model Context Protocol (MCP) server for WhatsApp. It enables AI to search and read personal WhatsApp messages (including images, videos, documents, and audio messages), search contacts, and send messages to individuals or groups. It connects directly to your personal WhatsApp account and operates via the WhatsApp Web multi-device API using the whatsmeow library. All messages are stored locally in an SQLite database, and only sent to the LLM (e.g., Claude) when accessed through tools. Designed for developers who need to integrate WhatsApp into AI systems.

Capabilities

▪Search and read WhatsApp messages
▪Search contacts
▪Send text messages
▪Send media files
▪Retrieve chat information

Use cases

Automatically reply to WhatsApp messagesManage WhatsApp contactsBackup WhatsApp messagesIntegrate WhatsApp into AI systems

Setup

Requires: GoPython 3.6+Anthropic Claude Desktop app 或 CursorUV (Python 包管理器)

1. Clone the repository: `git clone https://github.com/lharries/whatsapp-mcp.git`;
2. Run the WhatsApp bridge: `cd whatsapp-bridge && go run main.go`;
3. Configure the MCP server: edit the config file and save it to the appropriate directory;
4. Restart Claude Desktop or Cursor.

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.