Melbis Shop
Official# ๐ Melbis Shop โ self-hosted e-commerce with an AI agent on staff
**Melbis Shop** is a self-hosted e-commerce platform: your server, your domain, your data. A native **Windows back-office** and a **PHP storefront** share one business logic, and the package ships an **MCP server**, so an AI agent โ Claude Code, Goose, Cherry Studio, anything that speaks MCP โ works in your store as an employee: under a staff login, with that person's permissions, every action signed by their name.
Built since 2002 for stores with real teams: several suppliers and price lists, hundreds to hundreds of thousands of products, staff who must not see each other's data.
---
## ๐ฏ Who it is for
A seller who has outgrown a marketplace and wants an own channel next to it โ with a team of two to five people, suppliers' price lists and hundreds of SKUs. Not a page builder for a single product.
## โ๏ธ Installation is automatic
You do not touch a console. In the Windows client you enter three things โ the server's address, its root password and your domain โ and the client installs everything over SSH itself: Docker, nginx, MySQL, PHP, the SSL certificate, the store. Updates run the same way, from the same window. A clean Ubuntu VPS becomes a working store in one sitting.
Seven steps with screenshots, from renting a server to the first task for the agent: https://melbis.com/en/doc/install/start/
## ๐ค What the AI agent does here
- **56 MCP tools** in the box: project files (modules, templates, statics, images โ with version history), the database (pools of steps with locks and cache marks), catalogue trees, product files, storefront pages as a visitor sees them, and the platform documentation itself.
- **26 store tools with 244 commands** come with the demo store: products and prices, descriptions, catalogue and attributes, suppliers, orders, scheduler tasks, users, image profiles, batch import of goods and files.
- **Permissions per command.** Tools are data, not code: the owner grants each command to a person or a group. An employee with no database access still runs the agent โ inside their own rights.
- **A real run, with the log and screenshots:** one message in plain words โ the first working version of a store โ currencies, suppliers, a catalogue with 12 products, three roles with separate rights, a business-process roadmap โ in **24 min 45 s and 21.2k tokens**. Half an hour more: a redesign from a free third-party template. โ https://melbis.com/en/doc/install/ai_work/
### Connecting an MCP client
The MCP server (`MelbisMCP.exe`, stdio) is installed together with the Windows client โ nothing to download separately. In the client open *System โ Connection โ AI Assistant*: the ready configuration is there with a **Copy** button for Goose, Cherry Studio and other MCP applications; **Check Connection** tests the licence, the login and the rights and says in words what is missing. Claude Code needs no configuration at all โ the client writes `.mcp.json` into the store folder, open that folder as a project. The agent signs in under the person who runs it; there is no separate AI account, licence or password in the chat.
## ๐ What makes the platform different
- ๐งฎ **One business logic** for the storefront and the back-office: an order is calculated by the same code in the Windows app and on the site. Nothing to synchronise, nothing to diverge.
- ๐ **Permissions down to the operation, the hour of the day and the server load**, plus four independent access planes on every catalogue section โ descriptions, prices, placement, browse. Content managers never see purchase prices.
- โก **Batch back-office.** Staff load a slice of the catalogue into a local database, edit it like a spreadsheet โ bulk assignments, formulas per column โ and push the changes in one packet. The storefront runs almost read-only.
- ๐ง **Five-level cache** whose dependencies are collected automatically from the queries a module runs. Trick cache serves an older copy under a load spike; Smart cache refreshes ahead of expiry in a quiet moment.
- ๐ฆ **Versioned orders**, supplier warehouses and stock, tax rules on a territory tree, discount groups, customer groups with automatic loyalty rules, printed documents on FastReport.
- ๐ ๏ธ **A development environment inside the back-office**: modules, templates and statics edited on the server with version history, SQL consoles, per-module cache settings, AI help in the editor with any OpenAI-compatible model and your own key.
- ๐งฉ **Storefront on your stack**: the built-in PHP template engine, or Laravel on the same order logic โ [melbis/melbis-shop-laravel](https://github.com/melbis/melbis-shop-laravel).
- ๐ Interface in 8 languages; storefront content translated by hand or automatically.
## ๐ฅ๏ธ What is under the hood
- **Server:** Ubuntu with Docker โ nginx 1.26, PHP 8.3 on Apache, MySQL 8.4, Certbot for SSL. Installed and updated by the client; the same `setup.sh` and `update.sh` live in this repository.
- **Client:** a native Windows application with a local Firebird database per store.
- **AI agent:** any MCP-capable application on the same Windows machine. The MCP server is part of the client package; no separate licence.
## ๐ฐ Licensing
Free to install and run in demo mode. A licence is bound to a staff login, not to a computer, and starts at **1 โฌ per day**; monthly and yearly licences, full functionality in every plan: https://melbis.com/en/price/
---
## ๐ Links
- ๐ **Website:** [melbis.com](https://melbis.com/en/)
- ๐ **Documentation โ installation and the AI agent:** [melbis.com/en/doc/install/start](https://melbis.com/en/doc/install/start/)
- ๐ **Reference of the Windows client:** [melbis.com/help/en](https://melbis.com/help/en/)
- ๐ **Platform guide in Markdown:** [docs](https://github.com/melbis/melbis-shop/blob/master/docs/index.md)
- ๐ **Installation packages:** [melbis.com/en/download](https://melbis.com/en/download/)
- ๐ป **Releases:** [melbis/melbis-shop/releases](https://github.com/melbis/melbis-shop/releases)
- ๐ณ **Docker Hub:** [melbis/melbis-shop](https://hub.docker.com/r/melbis/melbis-shop)
- ๐ฆ **Packagist:** [melbis/melbis-shop](https://packagist.org/packages/melbis/melbis-shop)
- ๐งพ **System requirements:** [wiki](https://github.com/melbis/melbis-shop/wiki/System-requirements)
- ๐ฌ **Discussions:** [github.com/melbis/melbis-shop/discussions](https://github.com/melbis/melbis-shop/discussions)
- ๐ผ๏ธ **Screenshots:** [melbis.com/en/screenshots](https://melbis.com/en/screenshots/)
---
*Your server. Your domain. Your AI partner.*
TDQS
Scored across 56 tools
Every tool is namespaced by resource (html, static, image, php, db, memory, tool, shop, session) and action, so even similar operations are clearly distinguishable. Ambiguous pairs like tool_run vs shop_run are explicitly contrasted in their descriptions.
Most tools follow a predictable snake_case resource_action pattern, with consistent add/load/save/rename/remove verbs within each file type. A few names like engine_whole_load, engine_map_tree, engine_db_tables, and engine_search break the pattern but remain readable.
56 tools is a very large surface, far beyond the 16-25 'heavy' range, even for a broad shop-administration scope. The count will burden agent tool selection and could benefit from consolidation or grouping.
The set provides thorough CRUD/lifecycle coverage for templates, statics, images, PHP files, database operations, memory, custom tools, and shop access. Minor gaps remain: config is read-only, there is no session disconnect, and element files lack rename/update operations.