whatsapp-mcp is an open source Model Context Protocol (MCP) server that enables AI agents to interact directly with a user’s WhatsApp account through a structured interface. It acts as a bridge between WhatsApp and large language models, allowing controlled access to messages, chats, and contacts. whatsapp-mcp is composed of two main components: a Go-based bridge that connects to the WhatsApp Web API and stores data locally, and a Python-based MCP server that exposes tools for AI interaction. All message data is stored in a local SQLite database and is only accessed when explicitly requested through defined tools, giving users control over how their data is used. It supports both sending and receiving messages, including various media types such as images, audio, videos, and documents. It integrates with AI applications like Claude through MCP, enabling conversational automation and contextual message retrieval.
Features
- Local storage of WhatsApp messages using SQLite for controlled access
- Integration with AI agents through Model Context Protocol tools
- Ability to send and receive messages, including media files
- Search and retrieval of chats, contacts, and message history
- QR code authentication for secure WhatsApp account connection
- Modular architecture with Go bridge and Python MCP server