No install? Use cloud.anythingmcp.com directly.
Sign in, install the Magento (Adobe Commerce) in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Drive Magento 2 / Adobe Commerce from any AI agent: products, categories, orders, customers, stock. 12 tools, Bearer admin-token auth, per-store base URL.
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Magento (Adobe Commerce)、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Magento (Adobe Commerce) + Gemini
Drive Magento 2 / Adobe Commerce from any AI agent: products, categories, orders, customers, stock. 12 tools, Bearer admin-token auth, per-store base URL.
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
MAGENTO_BASE_URL, MAGENTO_ACCESS_TOKEN
步骤 1 — 获取凭证
magento.com).
Setup:
- As Magento admin → System → Integrations → Add New Integration.
- Name + email, then on the API tab pick scopes: at minimum Catalog (Products + Categories + Stock), Customers, Sales (Orders + Invoices + Shipments).
- Activate the integration → grant access. Magento generates an Access Token (this is the long-lived bearer token).
- Set:
MAGENTO_BASE_URL= your storefront base URL (e.g.https://shop.example.com)MAGENTO_ACCESS_TOKEN= the integration access token- Optionally
MAGENTO_STORE_VIEWif you want a specific store view (default 'default' or use 'all')
Authentication: Authorization: Bearer ${MAGENTO_ACCESS_TOKEN}.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—Magento (Adobe Commerce)应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
magento_search_products | Search products with Magento's search criteria DSL |
magento_get_product | Fetch a single product by SKU |
magento_create_product | Create a product |
magento_update_product | Update a product by SKU (PUT) |
magento_delete_product | Permanently delete a product by SKU |
magento_update_stock | Update inventory stock for a SKU at a source |
magento_list_categories | List the category tree (or below a rootCategoryId) |
magento_search_orders | Search orders |
magento_get_order | Fetch one order by ID with billing/shipping addresses, items[], status history |
magento_cancel_order | Cancel an order (only valid in pending/processing status) |
magento_search_customers | Search customers with the same DSL |
magento_get_customer | Fetch one customer by ID |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对您有帮助吗?