WhatsApp MCP Server

A Model Context Protocol (MCP) server for WhatsApp integration. Send messages, search conversations, and access your WhatsApp history through Claude and other LLMs.
接入你的智能体
從發布者安裝。不是 PlugMCP 端點。
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者

A Model Context Protocol (MCP) server for WhatsApp integration. Send messages, search conversations, and access your WhatsApp history through Claude and other LLMs.
MCP server enabling LLMs to interact with WhatsApp - send messages with fuzzy name matching, full-text search across conversations, manage chats and contacts, and download media
This MCP server provides 7 tools to interact with your WhatsApp account via the whatsmeow library:
All messages and chats are persisted to a local SQLite database with full-text search capabilities, enabling rich queries and analysis of your WhatsApp history.
# Pull the image
docker pull ghcr.io/eddmann/whatsapp-mcp:latest
# Create directory for persistent storage
mkdir -p whatsapp-store
# Run the container (QR code will be displayed)
docker run -it --rm \
-v "$(pwd)/whatsapp-store:/app/store" \
ghcr.io/eddmann/whatsapp-mcp:latest
On first run, a QR code will be displayed in the terminal:
store/whatsapp.db and persists across restartsstore/messages.db with FTS5 full-text searchstore/<chatJID>/ directoriesImportant: Mount a volume to
/app/storeto persist session data and messages across container restarts.
Add to your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"whatsapp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-v",
"/ABSOLUTE/PATH/TO/whatsapp-store:/app/store",
"ghcr.io/eddmann/whatsapp-mcp:latest"
]
}
}
}
{
"mcpServers": {
"whatsapp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-v",
"/ABSOLUTE/PATH/TO/whatsapp-store:/app/store",
"-e",
"LOG_LEVEL=DEBUG",
"ghcr.io/eddmann/whatsapp-mcp:latest"
]
}
}
}
DB_DIR - Directory for SQLite databases and downloaded media - default: storeLOG_LEVEL - Logging level (DEBUG, INFO, WARN, ERROR) - default: INFOFFMPEG_PATH - Path to ffmpeg binary for audio conversion - default: ffmpegAsk Claude to interact with your WhatsApp data using natural language.
"Send a message to John saying I'll be there in 10 minutes"
"Send a photo from ~/Desktop/photo.jpg to Bob"
"Send this audio recording to the Project Team group"
"Reply to that message from Sarah saying 'Sounds good!'"
Recipient Formats (with fuzzy name matching):
- Contact/group names:
"John","Bob","Project Team"(searches your chat history)- Phone numbers: Without
+(e.g.,447123456789)- Full JID:
[email protected]for contacts,[email protected]for groupsIf multiple matches are found for a name, you'll be prompted to disambiguate using the full JID.
Message Threading:
Reply to specific messages to create threaded conversations. The original message will be quoted in your reply.
"Show me my recent chats"
"List my last 20 messages with John"
"Show the conversation with Dad from yesterday with context"
"Search for all messages mentioning 'project deadline'"
"Find messages from Alice about the meeting"
"Search for 'birthday party' in my group chats"
"Download the latest photo from the Family group"
"Save that video Mick sent me yesterday"
"Catch me up on today's WhatsApp activity"
"Show me what happened in my WhatsApp groups this week"
"What questions have I been asked today?"
MIT License - see LICENSE file for details
This project is not affiliated with, endorsed by, or sponsored by WhatsApp Inc. or Meta Platforms, Inc. Use at your own risk. Ensure compliance with WhatsApp's Terms of Service when using this software.
Inspired by lharries/whatsapp-mcp
MCP server enabling LLMs to interact with WhatsApp - send messages with fuzzy name matching, full-text search across conversations, manage chats and contacts, and download media
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Whatsapp 透過 stdio 在本機執行。
上次檢查時間:2026-10-28。 MCP server enabling LLMs to interact with WhatsApp - send messages with fuzzy name matching, full-text search across conversations, manage chats and contacts, and download media