MCP server for Yango Tech Retail — inspect and manage stores, catalog, prices, stock and orders from an AI app
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add mcp-yango-retail -- npx -y mcp-yango-retail{
"mcpServers": {
"mcp-yango-retail": {
"command": "npx",
"args": ["-y", "mcp-yango-retail"],
"env": {
"YANGO_RETAIL_TOKEN": "<yango_retail_token>"
}
}
}
}YANGO_RETAIL_TOKENResumen de MCP Servers
# <img src="./assets/a1-logo.svg" alt="A1" width="40"> Yango Tech Retail MCP
**English** | [Русский](./README.ru.md)
[](https://www.npmjs.com/package/mcp-yango-retail)
[](https://github.com/A1-x-Tech/mcp-yango-retail/actions/workflows/ci.yml)
[](https://glama.ai/mcp/servers/A1-x-Tech/mcp-yango-retail)
[](./LICENSE)
**A1 Yango Tech Retail MCP** connects an AI app to a retailer account in Yango Tech Retail. Use ordinary language to check stores, orders, products, prices and stock, or to create orders and update account data when needed.
The server works with the retailer-facing B2B API for grocery retail and darkstores. It is not a marketplace seller portal, a taxi service or Yango Delivery.
- **16 tools.** Nine read-only tools, five write tools and two potentially destructive tools cover stores, catalog, pricing, stock, orders and receipts.
- **A safe read-only start.** Check connected data before changing anything in the account.
- **Clear write boundaries.** Order creation and cancellation, product upserts, price changes, discount creation and stock updates are separated from reads.
- **Additional API coverage.** Technical users can reach methods without a dedicated tool through `raw_request`.
Start with:
> List our stores and show the stock of product `[product ID]` in each.
[Connect the server](#quick-start) · [Explore use cases](#what-you-can-ask-it-to-do) · [Open technical documentation](#technical-documentation)
---
## See it work in a minute
> **You:** List our stores and show the stock of product `[product ID]` in each.
>
> **Assistant:** I will return the stores, their ids and the current stock of this product in each one.
>
> **You:** Show the price of this product in every price list.
>
> **Assistant:** I will return the price lists and the current product price in each one. No account data will be changed.
>
> **You:** Change the price to `99.90` in price list `[price-list ID]`.
>
> **Assistant:** This will change a real customer-facing price. I will show the product, price list, current value and new value before asking for confirmation.
>
> **You:** Confirm.
>
> **Assistant:** The price has been updated. I will read the price list again and return the current value.
> Stores, products, prices, stock and order states always come from the connected retailer account and the current API response.
## Contents
- [Quick start](#quick-start)
- [What you can ask it to do](#what-you-can-ask-it-to-do)
- [How retail data is connected](#how-retail-data-is-connected)
- [What changes in the account](#what-changes-in-the-account)
- [Getting access](#getting-access)
- [Configuration](#configuration)
- [Data and telemetry](#data-and-telemetry)
- [Limits and background work](#limits-and-background-work)
- [Technical documentation](#technical-documentation)
- [Support](#support)
## Quick start
You need Node.js 20+, a Yango Tech Retail account and a retailer Bearer token.
1. [Get a token](#getting-access) from your Yango Tech integration manager.
2. Add the server to your AI app using one of the instructions below.
3. Start with a read-only request:
> List our stores and show the stock of product `[product ID]` in each.
<details open>
<summary><strong>Codex</strong></summary>
<br>
**In the app:**
1. Open **Settings → Plugins → MCP servers**.
2. Select **Add server**.
3. Add the launch command `npx -y mcp-yango-retail@latest` and the `YANGO_RETAIL_TOKEN` environment variable with your token.
**From the command line:**
```bash
codex mcp add yango-retail \
--env YANGO_RETAIL_TOKEN=your_token \
-- npx -y mcp-yango-retail@latest
```
Check the connection:
```bash
codex mcp list
```
[Codex MCP documentation](https://learn.chatgpt.com/docs/extend/mcp?surface=cli)
</details>
<details>
<summary><strong>Claude Code</strong></summary>
<br>
```bash
claude mcp add \
--env YANGO_RETAIL_TOKEN=your_token \
--transport stdio \
--scope user \
yango-retail \
-- npx -y mcp-yango-retail@latest
```
Check the connection:
```bash
claude mcp list
```
[Claude Code MCP documentation](https://code.claude.com/docs/en/mcp)
</details>
<details>
<summary><strong>Claude Desktop</strong></summary>
<br>
1. Open Claude Desktop and go to **Settings → Developer**.
2. Select **Edit Config**.
3. Add the server to `mcpServers`:
```json
{
"mcpServers": {
"yango-retail": {
"command": "npx",
"args": ["-y", "mcp-yango-retail@latest"],
"env": {
"YANGO_RETAIL_TOKEN": "your_token"
}
}
}
}
```
If **Edit Config** is unavailable, open the configuration file directly:
- macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
- Windows: `%APPDATA%\Claude\claude_desktop_config.json`
[Claude Desktop MCP documentation](https://support.claude.com/en/articles/10949351-getting-started-with-local-mcp-servers-on-claude-desktop)
</details>
<details>
<summary><strong>Cursor</strong></summary>
<br>
Add a user-level server to `~/.cursor/mcp.json` on macOS/Linux or `%USERPROFILE%\.cursor\mcp.json` on Windows:
```json
{
"mcpServers": {
"yango-retail": {
"type": "stdio",
"command": "npx",
"args": ["-y", "mcp-yango-retail@latest"],
"env": {
"YANGO_RETAIL_TOKEN": "your_token"
}
}
}
}
```
[Cursor MCP documentation](https://cursor.com/docs/mcp)
</details>
<details>
<summary><strong>VS Code</strong></summary>
<br>
Run **MCP: Open User Configuration** from the Command Palette and add:
```json
{
"servers": {
"yango-retail": {
"type": "stdio",
"command": "npx",
"args": ["-y", "mcp-yango-retail@latest"],
"env": {
"YANGO_RETAIL_TOKEN": "${input:yango_retail_token}"
}
}
},
"inputs": [
{
"type": "promptString",
"id": "yango_retail_token",
"description": "Yango Tech Retail Bearer token",
"password": true
}
]
}
```
Check the server with **MCP: List Servers**.
[VS Code MCP documentation](https://code.visualstudio.com/docs/agent-customization/mcp-servers)
</details>
## What you can ask it to do
### Check stores and the product catalog
- List stores with their ids, status, location, address and name when available.
- Browse products by cursor and inspect their status, category, localized names, barcodes and custom attributes.
- Create or update up to 100 products in one request. Product records are upserted rather than added as duplicates.
### Check and update prices
- List price lists and read product prices from one or more lists.
- Compare the same product across price lists.
- Set up to 100 prices in one request using decimal strings such as `"150.00"`.
- Create up to 100 store-specific discounts after confirming the expected field structure with Yango Tech.
### Check and update stock
- Read stock across stores, including the product, quantity and shelf type.
- Update up to 1,000 stock lines for one store.
- Use `initialize` for the first stock load and `modify` for regular updates.
### Work with orders and receipts
- Create an order after collecting its store, products, quantities, prices, delivery details and payment type.
- Read order details and check the current states of several orders at once.
- Follow the order event feed for new orders, state changes and issued receipts.
- Read a fiscal receipt by order id or receipt id.
- Cancel an order after checking its current state and the cancellation reason.
### Use additional API methods
`raw_request` covers `/b2b/v1/*` methods without a dedicated tool, including order updates, VAT data, price-list links, picking, logistics and 3PL delivery operations. It can change real account data and is intended for technical users who understand the upstream API.
Complete schemas, response fields and API gaps are available in the [tool reference](docs/TOOLS.md).
## How retail data is connected
| Entity | How it is used |
|---|---|
| Store | Identifies the location whose stock and discounts are read or changed |
| Product | The same `product_id` connects catalog data, prices, stock and order items |
| Price list | Holds product prices separately from a store; store-to-list links use another API method |
| Stock line | Connects a product, store, quantity and shelf type; sellable stock normally uses `store` |
| Order | Uses a retailer-supplied `order_id`; order details and current state are read separately |
| Receipt | Can be requested by `order_id` or `receipt_id` when it is available |
Feeds use cursor pagination. A page with fewer items than the requested limit means the current product, price-list or stock feed is exhausted. The order event feed is continuous: keep its last cursor and request the next page later.
## What changes in the account
The server exposes MCP annotations for read-only, write and destructive actions. The AI client decides when and how to ask for confirmation.
| Action | Result | Changes the account |
|---|---|---:|
| Read stores, products, price lists, prices, stock, orders or receipts | Returns current account data | No |
| Create or update products | Upserts real catalog records | Yes |
| Set prices | Overwrites customer-facing prices | Yes |
| Create discounts | Adds real store-specific discounts | Yes |
| Update or initialize stock | Overwrites stock quantities for a store | Yes |
| Create an order | Adds a real order with the supplied `order_id` | Yes |
| Cancel an order | Changes the order to a cancellation state | Yes |
| `raw_request` | Calls another API method, including possible writes | Depends on the method |
Before a write, ask the assistant to show the target store, product ids, price list, quantities, current values and proposed values. Write responsesLo que la gente pregunta sobre mcp-yango-retail
¿Qué es A1-x-Tech/mcp-yango-retail?
+
A1-x-Tech/mcp-yango-retail es mcp servers para el ecosistema de Claude AI. MCP server for Yango Tech Retail — inspect and manage stores, catalog, prices, stock and orders from an AI app Tiene 0 estrellas en GitHub y su última actualización registrada es del 2026-08-18.
¿Cómo se instala mcp-yango-retail?
+
Puedes instalar mcp-yango-retail clonando el repositorio (https://github.com/A1-x-Tech/mcp-yango-retail) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar A1-x-Tech/mcp-yango-retail?
+
Nuestro agente de seguridad ha analizado A1-x-Tech/mcp-yango-retail y le ha asignado un Trust Score de 95/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene A1-x-Tech/mcp-yango-retail?
+
A1-x-Tech/mcp-yango-retail es mantenido por A1-x-Tech. La última actividad registrada en GitHub es del 2026-08-18, con 0 issues abiertos.
¿Hay alternativas a mcp-yango-retail?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega mcp-yango-retail en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/a1-x-tech-mcp-yango-retail)<a href="https://claudewave.com/repo/a1-x-tech-mcp-yango-retail"><img src="https://claudewave.com/api/badge/a1-x-tech-mcp-yango-retail" alt="Featured on ClaudeWave: A1-x-Tech/mcp-yango-retail" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!