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.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → Ecwid klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
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.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
ECWID_STORE_ID, ECWID_TOKEN
Schritt 1 — Zugangsdaten holen
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)
Schritt 2 — Adapter installieren
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Schritt 3 — Connector in Gemini hinzufügen
Gemini CLI liest MCP-Server aus ~/.gemini/settings.json (oder %APPDATA%\gemini\settings.json unter Windows). Hinzufügen:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Hole deinen MCP API Key aus AnythingMCP → Profil → MCP API Keys → Neuer Key.
- Speichern und
geminineu starten. /mcpin Gemini CLI ausführen —Ecwidsollte als verfügbar gelistet sein.- Vertex AI Studio:
https://cloud.anythingmcp.com/mcpimtools-Array der Anfrage mit demselben Bearer-Header übergeben.
Verfügbare Tools
| 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
Unterstützen Gemini 1.5 Pro oder 2.x MCP? Ja — Gemini CLI ≥ 0.4 und die Vertex AI Tools API akzeptieren MCP httpUrl-Connectors mit Bearer-Header.
Nächste Schritte
War dieser Guide hilfreich?