---
title: "Deploy WACrew"
description: "Open-source WhatsApp AI agent with a chat panel and an MCP server"
category: "AI/ML"
url: https://railway.com/deploy/wacrew
---

# Deploy WACrew

Open-source WhatsApp AI agent with a chat panel and an MCP server

**[Deploy WACrew on Railway](https://railway.com/template/wacrew)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/wacrew/manifest.json

- **Creator:** Rodrigo Shodi Sumioshi's Projects
- **Category:** AI/ML
- **Total deploys:** 1

## Template content

### wacrew https://wacrew.com.br/assets/logo/wacrew-mark.svg

- **Image:** ghcr.io/sumioshi/wacrew:latest
- **Health check:** /login
- **Public domain:** Yes

## Documentation

# Deploy and Host WACrew on Railway

WACrew is an open-source WhatsApp AI agent. It connects to your own WhatsApp account by QR code, keeps the history of the chats you pick in a web panel, and lets AI clients like Claude and Cursor use them through an MCP server. Every reply the agent writes goes through a review before it is sent, at a human pace.

## About Hosting WACrew

WACrew only records what arrives while it is running, so it needs to stay online. This template runs the prebuilt image `ghcr.io/sumioshi/wacrew` as a single service with a volume at `/data`, where the WhatsApp session, messages and media live. Redeploys and image updates keep that volume, so you scan the QR code once. The panel has a login. The username is `admin`, and the password is generated for you in the `PANEL_PASS` variable. After the deploy, open the public URL, sign in, go to `/config`, scan the QR code and pick the chats to follow.

## Common Use Cases

- Give Claude or Cursor read and reply access to your WhatsApp through MCP
- Keep a searchable history of client groups, with media and audio transcripts
- Let an AI agent answer routine messages while you review anything sensitive

## Dependencies for WACrew Hosting

- A WhatsApp account to link (personal or Business app)
- Optional: an OpenRouter API key in `OPENROUTER_API_KEY` to transcribe audio

### Implementation Details

To use the cloud panel from your local AI client, install the MCP package and point it at your Railway URL:

```bash
WAC_CLOUD_URL=https://.up.railway.app WAC_CLOUD_USER=admin WAC_CLOUD_PASS= npx -y wacrew-mcp
```

Source code, docs and the MCP tool list: https://github.com/sumioshi/wacrew

## Why Deploy WACrew on Railway?


Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying WACrew on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.



## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [Weaviate](https://railway.com/deploy/weaviate-1) — Vector database with hybrid search and an API key-protected API
- [Möbius Personal AI OS](https://railway.com/deploy/mobius-v01-personal-ai-os) — Self-hosted AI agent that builds and runs apps for you, with memory.

Open this page in a browser: https://railway.com/deploy/wacrew