WaPulse WhatsApp MCP Server
A Model Context Protocol server that integrates with WaPulse WhatsApp Web API, enabling users to send messages, manage groups, handle files, and perform various WhatsApp operations programmatically.
README
WaPulse WhatsApp MCP Server
A comprehensive Model Context Protocol (MCP) server that provides seamless integration with the WaPulse WhatsApp Web API. This server enables you to send messages, manage groups, handle files, and perform various WhatsApp operations through the MCP protocol.
Features
🚀 25 WhatsApp Tools Available
Messaging Tools (7)
send_whatsapp_message- Send text messages to individuals or groupssend_whatsapp_files- Send images, documents, and other filessend_whatsapp_audio- Send audio messages and voice notesload_chat_messages- Retrieve chat history and messagescheck_id_exists- Verify if a WhatsApp ID existsvalidate_phone_number- Validate phone number formatget_all_chats- Get all chat conversations
Group Management Tools (12)
create_whatsapp_group- Create new WhatsApp groupsadd_group_participants- Add members to groupsremove_group_participants- Remove members from groupspromote_group_participants- Promote members to admindemote_group_participants- Demote admins to membersleave_whatsapp_group- Leave a groupget_group_invite_link- Get group invite linkschange_group_invite_code- Generate new invite linksget_group_requests- View pending join requestsapprove_group_request- Approve join requestsreject_group_request- Reject join requestsget_all_groups- List all groups
Instance Management Tools (5)
create_instance- Create new WhatsApp instancesget_qr_code- Get QR code for WhatsApp Web connectionstart_instance- Start a WhatsApp instancestop_instance- Stop a WhatsApp instancedelete_instance- Delete a WhatsApp instance
General Tools (2)
get_wapulse_documentation- Access API documentationget_all_chats- Retrieve all chat conversations
Installation
Option 1: One-Click Cursor Installation (Easiest)
Click this link to automatically install in Cursor IDE:
📱 Install WaPulse MCP in Cursor
After clicking:
- Cursor will install the server automatically
- Edit your
~/.cursor/mcp.jsonfile - Replace
"enter-your-wapulse-token-here"with your actual WaPulse token - Replace
"enter-your-instance-id-here"with your actual instance ID - Restart Cursor
Option 2: NPX (Manual)
Install directly via NPX with your WaPulse credentials:
npx wapulse-whatsapp-mcp-server
Configuration via Environment Variables:
export WAPULSE_TOKEN="your-wapulse-token"
export WAPULSE_INSTANCE_ID="your-instance-id"
export WAPULSE_BASE_URL="https://wapulseserver.com:3003" # optional
npx wapulse-whatsapp-mcp-server
Configuration in MCP Client (Cursor):
Add to your mcp.json:
{
"mcpServers": {
"wapulse": {
"command": "npx",
"args": ["wapulse-whatsapp-mcp-server"],
"env": {
"WAPULSE_TOKEN": "your-wapulse-token",
"WAPULSE_INSTANCE_ID": "your-instance-id"
}
}
}
}
Option 3: Smithery Cloud
Install via Smithery cloud (requires Smithery account):
npx @smithery/cli@latest install @Quegenx/wapulse-whatsapp-mcp --client cursor
Option 4: Local Development
- Clone the repository:
git clone https://github.com/Quegenx/wapulse-mcp.git
cd wapulse-mcp
- Install dependencies:
npm install
- Build the project:
npm run build
- Configure your MCP client to use the built server at
dist/smithery-index.jswith your WaPulse credentials
Configuration
Required Configuration
wapulseToken- Your WaPulse API tokenwapulseInstanceID- Your WhatsApp instance ID
Optional Configuration
wapulseBaseUrl- WaPulse API base URL (defaults tohttps://wapulseserver.com:3003)
Example MCP Client Configuration
For Cursor IDE, add to your mcp.json:
{
"mcpServers": {
"wapulse-whatsapp": {
"command": "npx",
"args": [
"-y",
"@smithery/cli@latest",
"run",
"@Quegenx/wapulse-whatsapp-mcp",
"--key",
"your-smithery-key",
"--profile",
"your-profile"
]
}
}
}
Usage Examples
Send a WhatsApp Message
// Send a text message
await sendWhatsAppMessage({
to: "972512345678",
message: "Hello from MCP!",
type: "user"
});
Send Files
// Send an image with caption
await sendWhatsAppFiles({
to: "972512345678",
files: [{
file: "data:image/jpeg;base64,/9j/4AAQ...",
filename: "image.jpg",
caption: "Check out this image!"
}]
});
Create a WhatsApp Group
// Create a new group
await createWhatsAppGroup({
name: "My New Group",
participants: ["972512345678", "972587654321"]
});
Load Chat Messages
// Get chat history
await loadChatMessages({
id: "972512345678@c.us",
type: "user"
});
Phone Number Format
All phone numbers should be in international format without the + sign:
- ✅ Correct:
972512345678(Israel) - ✅ Correct:
14155552671(US) - ❌ Incorrect:
+972512345678 - ❌ Incorrect:
972-512-345-678
Error Handling
The server uses proper MCP error codes:
InvalidParams- For validation errors (invalid phone numbers, missing parameters)InternalError- For API failures or network issues
Development
Building
npm run build
Testing
npm test
Linting
npm run lint
API Documentation
The server includes a built-in documentation tool that provides comprehensive information about the WaPulse API:
await getWaPulseDocumentation({
section: "messaging", // overview, authentication, messaging, groups, instances, webhooks, errors, rate-limits, examples
search: "send message" // optional search term
});
Requirements
- Node.js 18+
- Valid WaPulse account and API credentials
- Active WhatsApp instance
Getting WaPulse Credentials
- Visit WaPulse.com
- Create an account and get your API token
- Create a WhatsApp instance and note the instance ID
- Use these credentials when installing the MCP server
Support
For issues related to:
- MCP Server: Open an issue on this repository
- WaPulse API: Contact WaPulse support
- WhatsApp Integration: Check WaPulse documentation
License
MIT License - see LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Built with ❤️ using the official Model Context Protocol SDK
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。