Mcpwhatsapp

This project builds a natural - language - based WhatsApp message sending and scheduling system through a client - server architecture. The server uses Mistral's LLM to parse user intentions and calls Twilio's API to send WhatsApp messages.

Communication tools Artificial intelligence chatbots #Natural language processing #Message scheduling #WhatsApp automation .Python

rating : 2.5 points

downloads : 8.2K

update time : 2025-04-28

Open Site

What is the WhatsApp MCP Assistant?

This is an AI - based WhatsApp message management system that allows users to automatically send or schedule WhatsApp messages through simple natural language instructions (e.g., 'Remind mom to take medicine at 3 PM tomorrow'). The system consists of a client and a server. The server uses Mistral's LLM to understand user intentions and sends messages via Twilio's API.

How to use the WhatsApp MCP Assistant?

Simply enter natural language instructions in the client, and the system will automatically parse your intentions and perform corresponding operations. There's no need to learn complex commands or interface operations.

Applicable scenarios

Suitable for scenarios that require scheduled or bulk sending of WhatsApp messages, such as personal reminders, business communication, and customer service automation. It's especially suitable for non - technical users who need natural language interaction.

Main features

Natural language interaction

You can operate using daily language without memorizing complex commands

Intelligent scheduling

Automatically recognize time information and set messages for scheduled sending

Cross - platform support

Supports WhatsApp Business API and enterprise - level functions through Twilio

Advantages

Use advanced messaging functions without programming knowledge

24/7 automatic response capability

Support natural language understanding of complex instructions

Limitations

Limited by Twilio API, pre - approved templates are required outside the 24 - hour window

Currently only supports the WhatsApp platform

Advanced features require a paid Twilio account

How to use

Install dependencies

Make sure Python and necessary libraries are installed

Configure the account

Fill in your Twilio API key and WhatsApp number in config.py

Start the service

Run the server first, then start the client

Usage examples

Business appointment reminder

Automatically remind customers of upcoming appointments

Personal schedule management

Set personal medication reminders

Frequently Asked Questions

Why did my message fail to send?

Does it support mass messaging?

What's the accuracy of scheduled messages?

Related resources

Twilio WhatsApp API documentation

Official WhatsApp API reference documentation

Mistral LLM project

Homepage of the used language model project

Template approval guide

How to create and submit message templates

🚀 WhatsApp MCP Assistant (Client-Server)

This project constructs a client-server pipeline to send and schedule WhatsApp messages via natural language. The server uses Mistral's large language model to interpret user intent and invokes Twilio to actually execute WhatsApp messaging.

🚀 Quick Start

Files

mcp_server.py: The main MCP server file that uses Mistral for intent parsing and calls Twilio to send messages.
mcp_client.py: A simple CLI client for interacting with the server through natural language.
config.py: Stores API keys and constants, including phone number configurations.

Server-Client Concept

The server uses Mistral's large language model to parse the user's intent and convert it into executable instructions (such as sending a message). The client is a CLI interface where users can enter prompts like "Send a message to Nir", and the backend automatically handles the subsequent operations.

Twilio

Twilio provides a programmable WhatsApp messaging API. In this project, it is used to actually send messages or simulate scheduling on WhatsApp.

⚠️ WhatsApp 24-Hour Window Limit (Twilio)

If you are using Twilio's WhatsApp API, please note that free-form messages (i.e., ordinary text messages) are only allowed to be sent within 24 hours after the user last communicated with your WhatsApp number.

If you try to send a message outside this window, you will see this error on the Twilio dashboard: "Cannot send free-form messages because you are outside the allowed time window. If you are using WhatsApp, use a message template."

✅ Solution

You must use a pre-approved message template to send messages outside the 24-hour window.
You can create message templates in Twilio Console > Messaging > Templates.

💡 When Testing Locally

If you are just testing on your own number and encounter problems, make sure you have recently sent a message from your WhatsApp to the Twilio number - this will reset the 24-hour window.

MCP Concept

The MCP server encapsulates a large language model (Mistral) with function call capabilities to dynamically route user intent to appropriate tools (sending/scheduling WhatsApp messages). The client allows prompt-based CLI input.