Advertise
MCP.so
Sign In

MCP WhatsApp Server

@pedsanches

Repository

Basic information

Category

Communication

Transports

stdio

Author

pedsanches

About MCP WhatsApp Server

No overview available yet

MCP WhatsApp Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-whatsapp-server": {
      "command": "python",
      "args": [
        "server.py"
      ]
    }
  }
}

MCP WhatsApp Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP WhatsApp Server?

MCP WhatsApp Server is an MCP (Model Context Protocol) server that integrates with WhatsApp via the Waha API, enabling AI assistants (such as Claude) to interact directly with WhatsApp contacts.

How to use MCP WhatsApp Server?

Install dependencies with pip install -r requirements.txt, set environment variables (WAHA_API_URL, WAHA_SESSION_ID, optional CONTATOS_FILE) in a .env file, configure contacts in a contatos.json file, start the Waha API, then run python server.py. Connect any MCP-compatible client to the server.

Key features of MCP WhatsApp Server

  • Check WhatsApp connection status
  • Send messages by phone number
  • Send messages by saved contact name
  • Manage contacts by name in a JSON file
  • View server configuration and contact list

Use cases of MCP WhatsApp Server

  • An AI assistant sending WhatsApp notifications to customers
  • Automating customer support replies based on contact names
  • Sending personalized bulk messages to a managed contact list
  • Monitoring the WhatsApp connection status remotely

Frequently asked questions

1

What are the system requirements for MCP WhatsApp Server?

Python 3.7 or higher, a running instance of the Waha API, and the Fast MCP library.

2

How do I configure MCP WhatsApp Server?

Set the environment variables `WAHA_API_URL` (default `http://localhost:3000`), `WAHA_SESSION_ID` (default `default`), and optionally `CONTATOS_FILE` in a `.env` file. Define contacts in a `contatos.json` mapping names to phone numbers.

3

How do I manage contacts in MCP WhatsApp Server?

Contacts are stored in a JSON file specified by `CONTATOS_FILE` (default `contatos.json`). You can also view the current contact list through the `waha://contatos` resource.

4

What resources and tools does MCP WhatsApp Server expose?

Resources: `waha://configuracao` (Waha API settings), `waha://status` (connection status), `waha://contatos` (contact list). Tools: `verificar_conexao_whatsapp()`, `enviar_mensagem_whatsapp(numero, mensagem)`, and `enviar_mensagem_por_nome(nome, mensagem)`.

5

How do I start MCP WhatsApp Server?

After installing dependencies and configuring the `.env` file, start the Waha API first (see its official instructions), then run `python server.py` in the project directory.

Comments

More Communication MCP servers

SomaCheck Vibecheck

Sensie-agents

Body language for AI agents, on your terms. A consented three-second phone gesture gives your agent an Aligned or Unaligned signal with confidence. You remain the authority.

1

uplika

uplika

Hosted MCP server that lets your AI agent post to Threads, Instagram, YouTube, Facebook, TikTok, Pinterest, Bluesky, Telegram, Discord, Ghost and Naver Blog. Setup for each agent.

JooVoice

JooVoice

Give your AI agent a phone. JooVoice makes real calls for you in 80+ languages, with local accents, across 67 countries, like booking a table, moving an appointment or chasing a refund, and sends back what happened. Call

MailTester Ninja

Unlimited & Limited

MailTester Ninja checks email addresses in real time by talking to the recipient's mail server, without sending a message, and keeps nothing afterwards. Agents can use it to clean a list, validate a signup, or find a con

Ghostedit

Ghostedit

Post to Instagram, TikTok, YouTube, Threads, LinkedIn, Bluesky and Mastodon from Claude, ChatGPT or Claude Code. Every post is checked against each platform's rules before it goes out, you can see what worked, and Instag

Advertise