@pnizer
基本情報
WhatsApp Web MCP Server
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"wweb-mcp": {
"command": "docker",
"args": [
"build",
".",
"-t",
"wweb-mcp:latest"
]
}
}
}Check WhatsApp client connection status
Send messages to WhatsApp contacts
Search for contacts by name or number
Retrieve messages from a specific chat
Get a list of all WhatsApp chats
Create a new WhatsApp group
Add participants to an existing group
Retrieve messages from a group
Send a message to a group
Search for groups by name, description, or member names
Get detailed information about a specific group
Download media from a message
Send a media message to a WhatsApp contact
A Node.js application that connects WhatsApp Web with AI models through the Model Context Protocol (MCP). It provides a standardized interface for programmatic interaction with WhatsApp, enabling automated messaging, contact management, and group chat functionality through AI-driven workflows.
Install globally via npm or use with npx. Alternatively, build with Docker. Run in one of three modes: WhatsApp API Server (REST), MCP Server (standalone direct connection), or MCP Server as API client (connects to the WhatsApp API Server). Configure using command-line options for transport (SSE or command), ports, and authentication. Scan a QR code with your WhatsApp mobile app for authentication. For Claude Desktop integration, add the appropriate NPX or Docker configuration including the API key.
No. The README explicitly states the tool is for testing purposes only and should not be used in production environments. It also notes that WhatsApp does not allow bots or unofficial clients, so using it may result in account blocking.
Two strategies: `local` (recommended) scans the QR code once and persists credentials between sessions; `none` requires scanning the QR code on each startup and is suitable for testing.
Yes. You can configure a webhook by creating a `webhook.json` file in the authentication data directory. The webhook supports filtering by allowed numbers, private messages, and group messages.
First, start the WhatsApp API server and note the API key from the logs. Then add an MCP server entry in your Claude Desktop configuration using either npx (with `--mcp-mode api` and the API key) or Docker (mounting a volume for authentication data).
The tool requires Node.js (run via npm/npx) or Docker. It supports two MCP transport modes: `sse` (HTTP server) and `command` (stdio). The WhatsApp API server uses port 3001 by default, and the SSE server uses port 3002.
call4me lets your AI agent make real phone calls for you. Ask Claude, ChatGPT, Cursor, Codex or your own app to book a table, schedule a dentist appointment, cancel a subscription or ask a business a question. It calls,
RelayLink lets your AI assistant send briefings to other people's AI assistants. Draft a package from your current conversation, attach files, approve the note, and the recipient's AI gets the full context: decisions, op
Send, receive and track real faxes in the US and Canada from Claude, ChatGPT or Cursor.
MCP server for the eSIMfly Business API — let Claude, Cursor and other AI agents search eSIM plans, check usage, diagnose connectivity and (optionally) order
HelpWell connects AI assistants to your help desk, knowledge base, live chat support and email marketing automation for SaaS. Triage support tickets, draft help docs and replies, manage contacts, and prepare newsletters
コメント