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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.