Whatify MCP Server
Exposes Whatify's WhatsApp API as tools for MCP-compatible AI clients, enabling sending messages, templates, and flows, and reading contacts, conversations, campaigns, and wallet balance.
README
Whatify MCP Server
An MCP (Model Context Protocol) server that exposes Whatify's WhatsApp API — sending messages, templates, and Flows, plus reading contacts, conversations, campaigns, and wallet balance — as tools for MCP-compatible AI clients (Claude Desktop, Claude Code, etc.).
It's a thin wrapper around the existing v1/external REST API
(app/Http/Controllers/Api/ExternalApiController.php), authenticated the same way:
an API key generated from Settings → API Keys in the Whatify dashboard.
Tools
| Tool | Maps to | Notes |
|---|---|---|
whatify_ping |
GET /ping |
Connectivity/auth check |
whatify_send_message |
POST /send-message |
Free-form text |
whatify_send_template |
POST /send-template |
Approved templates only |
whatify_send_flow |
POST /send-flow |
WhatsApp Flow (interactive form) |
whatify_message_status |
GET /messages/{id} |
Delivery status |
whatify_list_templates |
GET /templates |
|
whatify_list_flows |
GET /flows |
|
whatify_list_contacts |
GET /contacts |
|
whatify_get_contact |
GET /contacts/{id} |
|
whatify_create_contact |
POST /contacts |
|
whatify_update_contact |
PUT /contacts/{id} |
|
whatify_list_conversations |
GET /conversations |
|
whatify_get_conversation_messages |
GET /conversations/{id}/messages |
|
whatify_list_campaigns |
GET /campaigns |
|
whatify_get_campaign |
GET /campaigns/{id} |
Includes delivery/read rate |
whatify_wallet_balance |
GET /wallet/balance |
send_flow and reading flows require the API key to have the send_flow /
read_flows permissions (added alongside this server — check the boxes when
generating a key in Settings → API Keys).
Setup
- Get an API key: log into Whatify → Settings → API Keys → generate a key with
the permissions you want the AI tool to have (e.g.
send_message,send_template,send_flow,read_contacts). - Install dependencies:
cd mcp-server npm install - Configure environment variables:
WHATIFY_API_KEY— the key from step 1 (required)WHATIFY_API_BASE_URL— defaults tohttp://localhost/api/v1/external; set this to your real app URL, e.g.https://whatify.in/api/v1/external
Using with Claude Desktop / Claude Code
Add to your MCP client config (e.g. claude_desktop_config.json, or via
claude mcp add for Claude Code):
{
"mcpServers": {
"whatify": {
"command": "node",
"args": ["C:/xampp/htdocs/whatify/mcp-server/src/index.js"],
"env": {
"WHATIFY_API_KEY": "wk_xxxxxxxxxxxxxxxx",
"WHATIFY_API_BASE_URL": "https://whatify.in/api/v1/external"
}
}
}
}
Restart the client, then ask it to send a message, e.g.:
"Using Whatify, send a WhatsApp message to +91XXXXXXXXXX saying the order has shipped."
Manual test
You can talk to the server directly over stdio for debugging:
npm start
then send newline-delimited JSON-RPC (initialize, tools/list, tools/call) on
stdin. Easier: use the MCP Inspector:
npx @modelcontextprotocol/inspector node src/index.js
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。