🟢 WA MCP

The first WhatsApp integration built natively for AI Agents.
Full MCP server exposing WhatsApp as discoverable tools, resources, and real-time notifications.

Quick Start • Features • Tools • Architecture • Configuration • Docker • Contributing

License

🤖 What is WA MCP?

WA MCP is a WhatsApp MCP server built with TypeScript that gives AI agents full access to WhatsApp through the Model Context Protocol. It supports both Baileys (WhatsApp Web) and Meta Cloud API as dual-channel backends, deployable with Docker in a single command.

Your agent connects once and auto-discovers 63 tools, 10 resources, and 12 real-time events — zero configuration, zero REST wrappers, zero glue code.

hljs

Your AI Agent ←→ MCP Protocol ←→ WA MCP ←→ WhatsApp

Instead of writing HTTP clients, parsing webhook payloads, and mapping endpoints to tools manually — your agent just connects and goes. Works out of the box with Claude, Google ADK, LangChain, and any MCP-compatible AI agent framework.

💡 MCP (Model Context Protocol) is the open standard for connecting AI agents to tools and data. WA MCP speaks MCP natively via Streamable HTTP and stdio transports.

🚀 Quick Start

One command with Docker

hljs language-bash

docker compose up

That's it. WA MCP + Redis, ready on http://localhost:3000/mcp.

Or run locally

hljs language-bash

# Prerequisites: Node.js >= 22, Redis running
npm install
cp .env.example .env

# Development (stdio transport)
npm run dev

# Production (HTTP transport)
npm run build && npm start

Connect your agent

🐍 Google ADK (Python)

hljs language-python

from google.adk.tools.mcp_tool import McpToolset

tools = McpToolset(url="http://localhost:3000/mcp")

# Agent auto-discovers 63 WhatsApp tools
# wa_create_instance, wa_send_text, wa_send_image, ...

🦜 LangChain

hljs language-python

from langchain_mcp import McpToolkit

toolkit = McpToolkit(server_url="http://localhost:3000/mcp")
tools = toolkit.get_tools()

💻 Claude Desktop

Add to your claude_desktop_config.json:

hljs language-json

{
  "mcpServers": {
    "whatsapp": {
      "command": "node",
      "args": ["path/to/wa-mcp/dist/index.js"],
      "env": {
        "WA_TRANSPORT": "stdio",
        "WA_REDIS_URL": "redis://localhost:6379"
      }
    }
  }
}

✨ Features

	Feature	Description
🔌	MCP-native	Streamable HTTP + stdio transports. No REST, no webhooks.
📱	Dual-channel	Baileys (WhatsApp Web) + Meta Cloud API — same interface.
🔄	Multi-instance	Run 1–50 WhatsApp numbers from a single server.
📨	Full messaging	Text, images, video, audio, documents, polls, reactions, replies, forwards, edits, deletes, view-once.
👥	Groups	Create, manage members, promote/demote admins, settings, invite links, join requests, ephemeral messages.
👤	Contacts & Profile	Number check, block/unblock, business profiles, privacy, status updates.
📡	Real-time events	12 notification types via SSE: messages, typing, groups, calls, connection status.
⚡	Rate limiting	BullMQ queues prevent WhatsApp bans (20 msg/min Baileys, 80 msg/min Cloud).
🔁	Auto-reconnect	Automatic reconnection with exponential backoff.
🗃️	Persistent	SQLite storage for sessions, messages, contacts, groups.
🐳	Single container	`docker compose up` — only Redis as external dependency.

🛠️ Tools

WA MCP exposes 63 tools across 9 domains. All tools use the wa_ prefix.

📋 Instance Management (8 tools)

Tool	Description
`wa_create_instance`	Create a new WhatsApp connection
`wa_connect_instance`	Connect (generates QR code)
`wa_disconnect_instance`	Gracefully disconnect
`wa_delete_instance`	Permanently remove instance
`wa_restart_instance`	Disconnect + reconnect
`wa_get_qr_code`	Get QR as base64 (Baileys)
`wa_get_pairing_code`	Get pairing code (Baileys)
`wa_set_cloud_credentials`	Set Cloud API token

💬 Messaging (17 tools)

Tool	Description
`wa_send_text`	Send text message
`wa_send_image`	Send image with caption
`wa_send_video`	Send video with caption
`wa_send_audio`	Send audio / voice note
`wa_send_document`	Send file / document
`wa_send_location`	Send GPS location
`wa_send_contact`	Send vCard contact
`wa_send_poll`	Create a poll
`wa_send_reaction`	React with emoji
`wa_send_link_preview`	Send URL with preview
`wa_forward_message`	Forward a message
`wa_edit_message`	Edit sent message
`wa_delete_message`	Delete message
`wa_pin_message`	Pin a message
`wa_send_view_once`	Send view-once media
`wa_send_presence`	Show typing / recording
`wa_mark_read`	Mark messages as read

💭 Chat Management (6 tools)

Tool	Description
`wa_get_messages`	Get chat message history
`wa_archive_chat`	Archive / unarchive
`wa_pin_chat`	Pin / unpin chat
`wa_mute_chat`	Mute / unmute
`wa_delete_chat`	Delete chat
`wa_clear_chat`	Clear chat history

👥 Groups (14 tools)

Tool	Description
`wa_create_group`	Create group
`wa_group_add_participants`	Add members
`wa_group_remove_participants`	Remove members
`wa_group_promote`	Promote to admin
`wa_group_demote`	Demote from admin
`wa_group_update_subject`	Change group name
`wa_group_update_description`	Change description
`wa_group_update_settings`	Change settings
`wa_group_leave`	Leave group
`wa_group_get_invite_code`	Get invite link
`wa_group_revoke_invite`	Revoke invite link
`wa_group_join`	Join via invite code
`wa_group_toggle_ephemeral`	Toggle disappearing messages
`wa_group_handle_request`	Approve / reject join request

📇 Contacts (5 tools)

Tool	Description
`wa_search_contact`	Search contacts by name or phone
`wa_check_number_exists`	Check if number is on WhatsApp
`wa_block_contact`	Block contact
`wa_unblock_contact`	Unblock contact
`wa_get_business_profile`	Get business profile

👤 Profile (5 tools)

Tool	Description
`wa_update_profile_picture`	Set profile picture
`wa_remove_profile_picture`	Remove profile picture
`wa_update_profile_name`	Change display name
`wa_update_profile_status`	Change status text
`wa_update_privacy`	Update privacy settings

📢 Status / Stories (3 tools)

Tool	Description
`wa_send_text_status`	Post text status
`wa_send_image_status`	Post image status
`wa_send_video_status`	Post video status

📰 Newsletter (3 tools)

Tool	Description
`wa_newsletter_follow`	Follow a newsletter
`wa_newsletter_unfollow`	Unfollow a newsletter
`wa_newsletter_send`	Send to newsletter

📞 Calls (1 tool)

Tool	Description
`wa_reject_call`	Reject incoming call

📖 Resources

Resources expose read-only WhatsApp state via whatsapp:// URIs:

URI	Description
`whatsapp://instances`	List all instances
`whatsapp://instances/{id}`	Instance details + queue stats
`whatsapp://instances/{id}/contacts`	All contacts
`whatsapp://instances/{id}/chats`	Active conversations
`whatsapp://instances/{id}/groups`	All groups
`whatsapp://instances/{id}/groups/{gid}`	Group metadata
`whatsapp://instances/{id}/messages/{chatId}`	Message history
`whatsapp://instances/{id}/profile`	Own profile
`whatsapp://instances/{id}/privacy`	Privacy settings
`whatsapp://instances/{id}/blocklist`	Blocked contacts

📡 Real-time Notifications

Events are pushed to agents via SSE (Server-Sent Events):

Event	Trigger
`whatsapp/message.received`	New incoming message
`whatsapp/message.updated`	Status change (sent → delivered → read)
`whatsapp/message.deleted`	Message deleted
`whatsapp/message.reaction`	Emoji reaction added/removed
`whatsapp/message.edited`	Message edited
`whatsapp/presence.updated`	Typing / recording / online
`whatsapp/chat.updated`	Chat metadata changed
`whatsapp/group.updated`	Group info changed
`whatsapp/group.participants_changed`	Member add/remove/promote/demote
`whatsapp/contact.updated`	Contact info changed
`whatsapp/connection.changed`	Instance status change (includes QR as base64)
`whatsapp/call.received`	Incoming call

🏗️ Architecture

hljs language-scss

┌─────────────────────────────────────────────┐
│              AI Agent Runtime               │
│    (Google ADK, Claude, LangChain, ...)     │
└──────────────────┬──────────────────────────┘
                   │  MCP Streamable HTTP
┌──────────────────▼──────────────────────────┐
│              WA MCP Server                  │
│                                             │
│  ┌────────────────────────────────────────┐ │
│  │  Layer 1 — MCP Transport (HTTP/stdio) │ │
│  ├────────────────────────────────────────┤ │
│  │  Layer 2 — MCP Core                   │ │
│  │  63 Tools │ 10 Resources │ 12 Events  │ │
│  ├────────────────────────────────────────┤ │
│  │  Layer 3 — Services                   │ │
│  │  Instance Manager │ Queue │ Dedup     │ │
│  ├────────────────────────────────────────┤ │
│  │  Layer 4 — Channel Abstraction        │ │
│  │  ┌──────────────┐ ┌────────────────┐  │ │
│  │  │   Baileys    │ │   Cloud API    │  │ │
│  │  │  (WebSocket) │ │    (HTTPS)     │  │ │
│  │  └──────────────┘ └────────────────┘  │ │
│  └────────────────────────────────────────┘ │
│       SQLite (Drizzle)    BullMQ (Redis)    │
└─────────────────────────────────────────────┘
                   │
                   ▼  WebSocket / HTTPS
          WhatsApp Servers

Dual-Channel Design

	Baileys	Cloud API
Protocol	WhatsApp Web (WebSocket)	Meta Official (HTTPS)
Auth	QR Code / Pairing Code	Access Token
Cost	Free	Per-conversation pricing
Compliance	Unofficial	Meta-approved
Best for	Dev, testing, low volume	Production, enterprise

Both backends implement the same ChannelAdapter interface. Your agent doesn't know or care which one is active — the tools work identically.

⚙️ Configuration

Copy .env.example to .env and configure:

Variable	Default	Description
`WA_TRANSPORT`	`http`	`http` (Streamable HTTP) or `stdio`
`WA_MCP_API_KEY`	—	Bearer token auth. Unset = no auth (dev)
`WA_MCP_PORT`	`3000`	HTTP server port
`WA_REDIS_URL`	`redis://localhost:6379`	Redis for BullMQ queues
`WA_LOG_LEVEL`	`info`	`debug` \| `info` \| `warn` \| `error`
`WA_BAILEYS_RATE_LIMIT`	`20`	Messages/min per Baileys instance
`WA_CLOUD_RATE_LIMIT`	`80`	Messages/min per Cloud API instance
`WA_MESSAGE_RETENTION_DAYS`	`30`	Auto-delete old messages
`WA_AUTO_RECONNECT`	`true`	Auto-reconnect on disconnect
`WA_MEDIA_CACHE_MAX_MB`	`500`	Media cache size limit
`WA_CLOUD_WEBHOOK_SECRET`	—	Meta webhook verification
`WA_CLOUD_WEBHOOK_PORT`	`3001`	Webhook receiver port
`WA_VERSION_CHECK`	`true`	Daily WhatsApp Web version check

🐳 Docker

Production

hljs language-bash

docker compose up -d

Services:

wa-mcp — The MCP server on port 3000
redis — BullMQ backend with AOF persistence

Health Check

hljs language-bash

curl http://localhost:3000/health

hljs language-json

{
  "status": "ok",
  "uptime": 3600,
  "instances": { "total": 3, "connected": 2, "disconnected": 1 },
  "version": "1.0.0"
}

Resource Requirements

Instances	RAM	CPU	Disk
1–5	256 MB	0.5 vCPU	1 GB
5–20	512 MB	1 vCPU	5 GB
20–50	1 GB	2 vCPU	10 GB

📁 Project Structure

hljs language-bash

src/
├── index.ts                     # Entry point (HTTP/stdio)
├── constants.ts                 # Defaults and limits
├── server/mcp.ts                # MCP server setup
├── tools/                       # 🔧 63 MCP tools (9 files)
├── resources/                   # 📖 10 MCP resources (8 files)
├── notifications/events.ts      # 📡 12 event types
├── channels/
│   ├── channel.interface.ts     # ChannelAdapter contract
│   ├── baileys/                 # Baileys implementation
│   └── cloud-api/               # Cloud API implementation
├── services/
│   ├── instance-manager.ts      # Instance lifecycle
│   ├── message-queue.ts         # BullMQ rate limiting
│   ├── dedup.ts                 # Message deduplication
│   └── media.ts                 # Media handling
├── db/
│   ├── schema.ts                # Drizzle table definitions
│   └── client.ts                # SQLite connection
├── schemas/                     # Zod validation (9 files)
└── types/                       # TypeScript definitions

🗺️ Roadmap

Phase 1 — Foundation: Baileys adapter, text messaging, QR auth, instance management
Phase 2 — Full messaging: all media types, dedup, reactions, edits, forwards
Phase 3 — Groups, contacts, profile, status/stories, newsletters
Phase 4 — Cloud API adapter: dual-channel unified interface
Phase 5 — Hardening: error recovery, CI/CD, tests, docs, v1.0 release
Phase 6 — Baileys v7 upgrade, LID support, contact sync, message persistence

🤝 Contributing

Contributions are welcome! Here's how the codebase is organized:

One file per domain — tools, resources, schemas, and channels each have domain-specific files
Zod schemas for everything — all tool inputs are validated with strict Zod schemas in src/schemas/
Both adapters — new features should be implemented in Baileys and stubbed in Cloud API
Layered architecture — tools → services → channels. No cross-layer imports.
Structured logging — use Pino, never console.log

hljs language-bash

# Development
npm run dev          # Start with stdio transport
npm run build        # Type-check + compile
npx tsc --noEmit     # Type-check only

📄 License

MIT — do whatever you want.

Built for the agentic era.
Stop writing REST wrappers. Let your agent discover WhatsApp.

wamcp

🟢 WA MCP

🤖 What is WA MCP?

🚀 Quick Start

One command with Docker

Or run locally

Connect your agent

✨ Features

🛠️ Tools

📖 Resources

📡 Real-time Notifications

🏗️ Architecture

Dual-Channel Design

⚙️ Configuration

🐳 Docker

Production

Health Check

Resource Requirements

📁 Project Structure

🗺️ Roadmap

🤝 Contributing

📄 License

Similar Packages

Tags

Original Author

Publisher