No install? Use cloud.anythingmcp.com directly.
Sign in, install the Ecwid 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 Ecwid (Lightspeed-owned e-commerce platform) from any AI agent: products, categories, orders, customers. 10 tools, OAuth2 Bearer auth, store-scoped URL.
💡 ¿Sin instalación? Usa cloud.anythingmcp.com directamente. Inicia sesión, pulsa Connectors → Ecwid, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
Ecwid + Gemini
Drive Ecwid (Lightspeed-owned e-commerce platform) from any AI agent: products, categories, orders, customers. 10 tools, OAuth2 Bearer auth, store-scoped URL.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
ECWID_STORE_ID, ECWID_TOKEN
Paso 1 — Obtener credenciales
ecwid.com).
Setup:
- Sign in to Ecwid → My Profile → My Apps → Create App (or use a personal Storefront API token from your Ecwid control panel).
- Note your Store ID (numeric) — visible in your Ecwid control panel URL.
- Set:
ECWID_STORE_ID= numeric store IDECWID_TOKEN= your access token (private personal token or OAuth2 access token)
Authentication: Authorization: Bearer ${ECWID_TOKEN}.
Store-scoped URL: https://app.ecwid.com/api/v3/{{ECWID_STORE_ID}}.
Product model: products have id, sku, name, price, originalPrice, costPrice, weight, quantity, unlimited (track stock?), enabled, inStock, categoryIds[], options[], variants[].
…(continued in the in-app connector instructions)
Paso 2 — Instalar el adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Paso 3 — Añadir el conector en Gemini
Gemini CLI lee servidores MCP desde ~/.gemini/settings.json (o %APPDATA%\gemini\settings.json en Windows). Añade:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Obtén tu MCP API key desde AnythingMCP → Perfil → MCP API Keys → Nueva Key.
- Guarda el archivo y reinicia
gemini. - Ejecuta
/mcpen la Gemini CLI —Ecwiddebería aparecer como disponible. - Vertex AI Studio: pasa
https://cloud.anythingmcp.com/mcpal arraytoolsde tu petición con el mismo header Bearer.
Herramientas disponibles
| Tool | What it does |
|---|---|
ecwid_get_profile | Get store profile (name, currency, formats, plan) |
ecwid_search_products | Search products with filters |
ecwid_get_product | Get a product by ID |
ecwid_create_product | Create a product |
ecwid_update_product | Update a product (PUT — full replacement of passed fields) |
ecwid_list_categories | List categories |
ecwid_search_orders | Search orders |
ecwid_get_order | Get an order by number |
ecwid_update_order | Update order — common: change paymentStatus, fulfillmentStatus, set trackingNumber |
ecwid_search_customers | Search customers |
FAQ
¿Gemini 1.5 Pro o 2.x soportan MCP? Sí — Gemini CLI ≥ 0.4 y la API de tools de Vertex AI aceptan conectores MCP httpUrl con header Bearer.
Siguientes pasos
¿Te ha sido útil esta guía?