Installation überspringen. In unter 2 Minuten einsatzbereit.
Starte eine kostenlose Testphase auf cloud.anythingmcp.com, füge Holded mit einem Klick hinzu und richte deinen KI-Client (Claude, ChatGPT, Copilot oder Cursor) auf den erzeugten MCP-Endpoint. Kein Docker, kein git clone, keinerlei Entwicklungserfahrung nötig.
Summary
Holded — the Spanish SMB business suite: contacts, sales and purchase documents, products, warehouses, treasury accounts and CRM funnels. REST API v1, API-key auth.
Frag einfach
Beispiel-Prompts für Holded
Klick auf einen Prompt, um ihn zu kopieren. In Claude, ChatGPT, Cursor, Gemini, Copilot oder OpenClaw einfügen — und gegen diesen Connector laufen lassen.
Claude ist KI und kann Fehler machen. Bitte Antworten gegenprüfen.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → Holded klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
Holded + Gemini
Holded — the Spanish SMB business suite: contacts, sales and purchase documents, products, warehouses, treasury accounts and CRM funnels. REST API v1, API-key auth.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
HOLDED_API_KEY
Schritt 1 — Zugangsdaten holen
Getting a key
- Sign in to Holded and open Configuración → Desarrolladores → API key (Settings → Developers).
- Generate a key and put it in
HOLDED_API_KEY. The key belongs to the account, not to a user, and carries full access to every module you have subscribed to — treat it as a password.
The key travels in a key header. Not Authorization, not a query parameter. Holded's own documentation calls it simply key.
…(continued in the in-app connector instructions)
Schritt 2 — Adapter installieren
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
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 —Holdedsollte 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 |
|---|---|
holded_list_contacts | List contacts — customers, suppliers, leads — with their name, NIF/CIF, e-mail, address and the type flags that say which role they hold |
holded_get_contact | Read one contact in full: tax data, billing address, payment terms, default VAT rate and the notes recorded against them |
holded_list_documents | List documents of one type — invoices, estimates, credit notes, purchase orders — with their number, date, contact, total and payment status |
holded_get_document | Read one document in full: every line with its quantity, price, discount and VAT, the totals, and the payments applied against it |
holded_list_products | List products and services with their SKU, name, price, cost, VAT rate and stock level |
holded_list_warehouses | List warehouses with their name and location, so a stock question can name the right one |
holded_list_treasury_accounts | List the treasury accounts (bank and cash) with their name, IBAN and current balance — the cash-position answer |
holded_list_funnels | List the CRM funnels with their stages, so a pipeline question knows which stages exist before asking about leads in them |
holded_list_leads | List CRM leads with their name, contact, value, funnel stage and expected close date — the sales-pipeline view |
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?
