Installation überspringen. In unter 2 Minuten einsatzbereit.
Starte eine kostenlose Testphase auf cloud.anythingmcp.com, füge Axonaut 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
Axonaut — French all-in-one CRM, invoicing and expense management for very small businesses: companies, employees, invoices, quotations, expenses, products and projects. REST API v2, API-key auth.
Frag einfach
Beispiel-Prompts für Axonaut
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 → Axonaut klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
Axonaut + Gemini
Axonaut — French all-in-one CRM, invoicing and expense management for very small businesses: companies, employees, invoices, quotations, expenses, products and projects. REST API v2, 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:
AXONAUT_API_KEY
Schritt 1 — Zugangsdaten holen
Getting a key
- Sign in to Axonaut and open Paramètres → API (Settings → API).
- Copy the key into
AXONAUT_API_KEY. It is account-wide and carries full access; treat it as a password.
The header is userApiKey. Not Authorization, not X-API-Key — Axonaut's own spelling, camel-cased, is what the server checks.
Axonaut calls customers 'companies' and people 'employees'. A company is a client or prospect organisation; an employee is a person attached to one. This trips people up, because 'employee' sounds like your own staff and is not.
…(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 —Axonautsollte 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 |
|---|---|
axonaut_list_companies | List companies — Axonaut's clients and prospects — with their name, SIRET, address, category and assigned user |
axonaut_get_company | Read one company in full: its addresses, custom fields, the employees attached to it and its accounting identifiers |
axonaut_list_employees | List employees — the people attached to client companies, not your own staff — with their name, e-mail, phone and role |
axonaut_list_invoices | List invoices with their number, date, company, pre-tax and total amounts and payment state |
axonaut_get_invoice | Read one invoice in full: every product line with quantity, price and VAT, the totals, and the payments recorded against it |
axonaut_list_quotations | List quotations (devis) with their number, date, company, total and whether they have been accepted |
axonaut_list_expenses | List expenses and supplier invoices with their date, supplier, category, pre-tax amount and VAT — the cost side of the ledger |
axonaut_list_products | List catalogue products with their reference, name, pre-tax price, VAT rate and stock quantity |
axonaut_list_projects | List projects with their name, company, budget, status and dates — the anchor for time and profitability questions |
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?
