mcp-zap
MCP server for sending and receiving WhatsApp messages through Evolution API, enabling management of instances, messages, and chats directly from Claude Code.
README
Evolution API MCP
MCP server para enviar e receber mensagens no WhatsApp direto do Claude Code, usando Evolution API (open-source, self-hosted).
O que faz
- Criar e gerenciar instancias WhatsApp
- Enviar mensagens de texto, midia, audio, localizacao, contatos, enquetes, stickers, botoes e listas
- Ler conversas e mensagens recebidas
- Reagir a mensagens, arquivar chats, marcar como lido
Pre-requisitos
- Docker Desktop
- Python 3.11+
- uv (gerenciador de pacotes Python)
- Claude Code
Instalacao
1. Subir a Evolution API
git clone https://github.com/SEU_USUARIO/evolution-api-mcp.git
cd evolution-api-mcp
docker compose up -d
Aguarde uns 15 segundos e teste:
curl http://localhost:8080/
Deve retornar {"status":200,"message":"Welcome to the Evolution API, it is working!"}.
2. Instalar o MCP server
uv venv
uv pip install -e .
3. Registrar no Claude Code
claude mcp add evolution-api -s user -- evolution-api-mcp
Ou adicione manualmente no arquivo ~/.claude.json:
{
"mcpServers": {
"evolution-api": {
"type": "stdio",
"command": "evolution-api-mcp",
"env": {
"EVOLUTION_API_URL": "http://localhost:8080",
"EVOLUTION_API_KEY": "evo_mcp_2024"
}
}
}
}
Windows: o command pode precisar ser o caminho completo do
.exe:C:/Users/SEU_USUARIO/evolution-api-mcp/.venv/Scripts/evolution-api-mcp.exe
4. Conectar seu WhatsApp
- Abra http://localhost:8080/manager/ no navegador
- Use a Global API Key:
evo_mcp_2024 - Crie uma instancia (ex: "meuwhats")
- Clique em "Gerar QR Code"
- Escaneie com seu WhatsApp: Configuracoes > Aparelhos conectados > Conectar dispositivo
5. Usar!
Reabra o Claude Code e comece a usar:
> envia uma mensagem pro 5511999999999 dizendo oi
> mostra minhas conversas recentes
> envia uma foto pra fulano
Configuracao
| Variavel | Descricao | Default |
|---|---|---|
EVOLUTION_API_URL |
URL da Evolution API | http://localhost:8080 |
EVOLUTION_API_KEY |
API key de autenticacao | (vazio) |
A API key padrao do Docker Compose e evo_mcp_2024. Mude no docker-compose.yml se quiser.
Estrutura
evolution-api-mcp/
├── docker-compose.yml # Evolution API + PostgreSQL
├── pyproject.toml # Dependencias Python
└── src/evolution_api_mcp/
├── server.py # MCP server (FastMCP + CodeMode)
├── client.py # HTTP client async
└── tools/
├── instance.py # Criar/conectar/deletar instancias
├── messages.py # Enviar texto, midia, audio, etc.
└── chat.py # Listar chats, ler mensagens
Tools disponiveis
Instance
create_instance- Criar instancia WhatsAppconnect_instance- Conectar e gerar QR codefetch_instances- Listar instanciasconnection_state- Verificar estado da conexaologout_instance- Desconectar WhatsApprestart_instance- Reiniciar instanciadelete_instance- Deletar instancia
Messages
send_text- Enviar textosend_media- Enviar imagem, video ou documentosend_audio- Enviar audio/nota de vozsend_location- Enviar localizacaosend_contact- Enviar cartao de contatosend_reaction- Reagir com emojisend_poll- Enviar enquetesend_buttons- Enviar botoes interativossend_list- Enviar lista interativasend_sticker- Enviar sticker
Chat
find_chats- Listar conversasfind_messages- Ler mensagens de um chatarchive_chat- Arquivar/desarquivar chatmark_message_as_read- Marcar como lido
Licenca
MIT
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.