This MCP server enables you to search and read your personal WhatsApp messages (including media such as images, videos, documents, and audio) and to send messages to individuals or groups. It connects to your personal WhatsApp account directly via the WhatsApp web multidevice API using the whatsmeow library. All messages are stored locally in a SQLite database within the whatsapp-bridge/store directory and are only exposed to an LLM when accessed through the provided MCP tools. The system comprises two main components: the Go-based WhatsApp Bridge, which handles authentication, message retrieval, and storing history; and the Python-based MCP server, which implements the Model Context Protocol and exposes standardized tools for Claude (or other LLMs) to interact with WhatsApp data. Tools include search_contacts, list_messages, list_chats, get_chat, get_direct_chat_by_contact, get_contact_chats, get_last_interaction, get_message_context, send_message, send_file, send_audio_message, and download_media. Media handling supports images, videos, documents, and audio; audio can be sent as playable voice messages in ogg opus format, converted automatically with FFmpeg if installed. The flow: Claude -> MCP server -> Go bridge/SQLite -> Claude.