WhatsApp Business MCP
Integrates with the Meta Cloud API (v24.0) to enable WhatsApp Business operations, using Meta access tokens and Business Account credentials for authentication, template management, and message sending capabilities.
Manages WhatsApp Business templates and messaging via the Meta Cloud API, providing tools to create, validate, list, delete, and check status of templates, as well as send template messages (including bulk sends) to phone numbers. Supports marketing and utility template types with various structural variants including carousels, catalogs, limited-time offers, and order details.
WhatsApp MCP Server
Manage WhatsApp Business templates and send messages from Claude, ChatGPT, Cursor, VS Code Copilot, or any MCP-compatible client — powered by the Meta Cloud API.
What It Does
Tool | Description |
| Validate a template payload before submitting to Meta |
| Submit a template for Meta approval |
| List templates with optional filters (status, category, name) |
| Get full details of a template by ID |
| Quick status check for a template |
| Delete a template by name |
| Send an approved template to a phone number |
| Send an approved template to multiple phone numbers |
8 tools covering the full template lifecycle: create → validate → approve → send.
Quick Start
1. Clone & Install
git clone https://github.com/nakulben/whatsapp-mcp.git
cd whatsapp-mcp
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt2. Configure Credentials
cp .env.example .envMETA_ACCESS_TOKEN=your_access_token
META_WABA_ID=your_whatsapp_business_account_id
META_PHONE_NUMBER_ID=your_phone_number_id
META_APP_ID=your_app_id # Optional, for media uploads
META_API_VERSION=v24.0 # Optional, defaults to v24.0Environment variables are used by all modes — local stdio and hosted remote.
How to get these? Go to Meta for Developers, create or select your app, navigate to WhatsApp > API Setup.
3. Connect to Your MCP Client
The server supports 3 transport modes:
Transport | Command | Used By |
|
| Claude Desktop, Cursor, VS Code, Windsurf |
|
| Legacy remote clients |
|
| Claude.ai, ChatGPT, newer MCP clients |
For HTTP transports, you can customize host/port:
python -m whatsapp_mcp --transport streamable-http --host 0.0.0.0 --port 8000Claude Desktop (stdio — local)
Add to claude_desktop_config.json:
{
"mcpServers": {
"whatsapp": {
"command": "/path/to/whatsapp-mcp/venv/bin/python",
"args": ["-m", "whatsapp_mcp"],
"env": {
"META_ACCESS_TOKEN": "your_access_token",
"META_WABA_ID": "your_waba_id",
"META_PHONE_NUMBER_ID": "your_phone_number_id",
"META_APP_ID": "your_app_id"
}
}
}
}Claude.ai Web (remote — streamable-http)
Claude.ai connects to remote MCP servers as custom connectors. The connection originates from Anthropic's cloud servers, not from your machine.
Host the server with env vars configured, behind HTTPS:
python -m whatsapp_mcp --transport streamable-http --host 0.0.0.0 --port 8001Put it behind HTTPS using nginx, Caddy, or a tunnel (ngrok, Cloudflare Tunnel)
In Claude.ai: go to Customize > Connectors → Add custom connector
Enter your server URL (e.g.
https://your-domain.com/mcp/)Claude supports authless or OAuth-based servers. For simplest setup, leave auth blank — the server will use the env vars you configured in step 1.
Note: Claude.ai does not support custom request headers. The server must be pre-configured with Meta credentials via environment variables. Each hosted server serves one WhatsApp Business Account.
location /mcp/ {
proxy_pass http://127.0.0.1:8001/;
proxy_http_version 1.1;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_read_timeout 86400;
}ChatGPT (remote — Responses API)
ChatGPT supports remote MCP servers via the Responses API. It supports both Streamable HTTP and SSE transports.
Option 1 — Server pre-configured with env vars (simplest):
from openai import OpenAI
client = OpenAI()
resp = client.responses.create(
model="gpt-4.1",
tools=[{
"type": "mcp",
"server_label": "whatsapp",
"server_url": "https://your-domain.com/mcp/",
"require_approval": "never",
}],
input="List all my approved templates",
)Option 2 — Per-request credentials via Bearer token:
Encode your Meta credentials as base64 JSON and pass them in the authorization field.
OpenAI forwards this value as the Authorization header to your MCP server:
# Create the token
echo -n '{"access_token":"EAA...","phone_number_id":"123","waba_id":"456"}' | base64
# Output: eyJhY2Nlc3NfdG9rZW4iOiJFQUEuLi4iLCJwaG9uZV9udW1iZXJfaWQiOiIxMjMiLCJ3YWJhX2lkIjoiNDU2In0=resp = client.responses.create(
model="gpt-4.1",
tools=[{
"type": "mcp",
"server_label": "whatsapp",
"server_url": "https://your-domain.com/mcp/",
"authorization": "eyJhY2Nlc3NfdG9rZW4iOiJFQUEuLi4iLCJwaG9uZV9udW1iZXJfaWQiOiIxMjMiLCJ3YWJhX2lkIjoiNDU2In0=",
"require_approval": "never",
}],
input="List all my approved templates",
)Note: ChatGPT only supports remote MCP servers (no local stdio). Your server must be publicly accessible over HTTPS.
Cursor (stdio)
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"whatsapp": {
"command": "/path/to/whatsapp-mcp/venv/bin/python",
"args": ["-m", "whatsapp_mcp"]
}
}
}VS Code Copilot (stdio)
Add to .vscode/mcp.json:
{
"servers": {
"whatsapp": {
"type": "stdio",
"command": "/path/to/whatsapp-mcp/venv/bin/python",
"args": ["-m", "whatsapp_mcp"]
}
}
}Per-Request Credentials (direct HTTP / curl / scripts)
For programmatic access or custom MCP clients, you can pass per-request credentials instead of relying on server env vars. Two methods are supported:
Method 1 — Bearer token (recommended):
Base64-encode a JSON object with your Meta credentials:
# Create the token
TOKEN=$(echo -n '{"access_token":"EAA...","phone_number_id":"123","waba_id":"456"}' | base64)
# Use it
curl -H "Authorization: Bearer $TOKEN" https://your-server.com/mcp/ ...Required fields: access_token, phone_number_id, waba_id. Optional: app_id, api_version.
Method 2 — X-Meta- headers:*
Header | Required | Description |
| Yes | Your Meta access token |
| Yes | Your WhatsApp phone number ID |
| Yes | Your WhatsApp Business Account ID |
| No | Your Meta app ID (for media uploads) |
| No | API version (defaults to v24.0) |
If neither Bearer token nor X-Meta-* headers are present, the server falls back to environment variables.
Usage Examples
Once connected, just talk to your AI assistant:
"Create a marketing template called
summer_salewith a header image, body text about 50% off, and a Shop Now button"
"List all my approved templates"
"Send the
order_confirmationtemplate to +919876543210 with order number ORD-456"
"Validate this template before I submit it: ..."
"Check the status of template ID 123456789"
Supported Template Types
Meta's API has 2 template categories(excluding Authentication). Within each category, templates can have different structural variants — each with its own component layout and validation rules.
Marketing Templates
Structural Variant | Create | Send | Key Components |
Text / Image / Video / Document | ✅ | ✅ | Header (optional) + Body + Footer + Buttons |
Carousel | ✅ | ✅ | Cards with per-card header, body, buttons |
Catalog | ✅ | ✅ | Body + |
Limited-Time Offer (LTO) | ✅ | ✅ | Body + |
Coupon Code | ✅ | ✅ | Body + |
Multi-Product Message (MPM) | ✅ | ✅ | Body + |
Single-Product Message (SPM) | ✅ | ✅ | Body + |
Product Card Carousel | ✅ | ✅ | Body + product cards with buttons |
Call Permission | ✅ | — | Body + |
Utility Templates
Structural Variant | Create | Send | Key Components |
Text / Image / Video / Document | ✅ | ✅ | Header (optional) + Body + Footer + Buttons |
Order Details | ✅ | ✅ | Body + |
Order Status | ✅ | ✅ | Body + order status parameters |
How routing works: When you call
create_template, the server inspects the components to auto-detect the structural variant (e.g., presence ofcards[]→ Carousel,CATALOGbutton → Catalog) and applies the correct validator. You just passcategory: "MARKETING"or"UTILITY"— the variant is determined from the component structure.
Running Tests
pip install pytest pytest-asyncio
python -m pytest tests/ -vProject Structure
whatsapp-mcp/
├── whatsapp_mcp/
│ ├── __init__.py # Package version
│ ├── __main__.py # Entry point (python -m whatsapp_mcp)
│ ├── config.py # Environment config loader
│ ├── meta_api.py # Async Meta Graph API client
│ ├── middleware.py # ASGI middleware for per-request credentials
│ ├── server.py # MCP server with 8 tools
│ ├── models/ # Pydantic data models
│ │ ├── body.py # Body component
│ │ ├── header.py # Header component (text/image/video/document)
│ │ ├── footer.py # Footer component
│ │ ├── buttons.py # Button types (URL, phone, quick reply, etc.)
│ │ ├── buttons_component.py
│ │ ├── enums.py # Template categories, types, formats
│ │ └── order_models.py # Order-related models (checkout templates)
│ └── validators/
│ ├── create/ # 12 template creation validators
│ └── send/ # 11 template send validators
├── tests/
│ ├── test_validators.py # Validator tests
│ ├── test_meta_api.py # API client tests (mocked HTTP)
│ └── test_tools.py # MCP tool registration & helper tests
├── .env.example
├── requirements.txt
├── LICENSE # MIT
└── ROADMAP.mdRequirements
Python 3.10+
Meta WhatsApp Business Account
System User access token with
whatsapp_business_messagingandwhatsapp_business_managementpermissions
Dependencies
Package | Purpose |
| Model Context Protocol SDK |
| Async HTTP client for Meta API |
| Payload validation |
| Environment config |
Roadmap
See ROADMAP.md for planned features.
License
MIT — see LICENSE.
Built by Jina Connect — the WhatsApp Business CX platform.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/nakulben/whatsapp-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server