Salta l'installazione. Attivo in meno di 2 minuti.
Avvia una prova gratuita su cloud.anythingmcp.com, aggiungi BuchhaltungsButler con un clic, poi punta il tuo client AI (Claude, ChatGPT, Copilot o Cursor) all'endpoint MCP generato. Niente Docker, niente git clone, nessuna esperienza di sviluppo richiesta.
Summary
BuchhaltungsButler — German automated bookkeeping: postings, receipts, bank transactions, customers and suppliers. Every endpoint is a POST; auth is HTTP Basic (API client id and secret) plus an api_key field in the request body.
Prova a chiedere
Prompt di esempio per BuchhaltungsButler
Clicca su un prompt per copiarlo. Incollalo in Claude, ChatGPT, Cursor, Gemini, Copilot o OpenClaw per eseguirlo contro questo connettore.
Claude è un'AI e può sbagliare. Verifica sempre le risposte.
💡 Niente installazione? Vai direttamente su cloud.anythingmcp.com. Accedi, clicca Connectors → BuchhaltungsButler, inserisci le credenziali, genera una MCP API key — fatto. Niente Docker, niente
git clone, niente server locale.
BuchhaltungsButler + Gemini
BuchhaltungsButler — German automated bookkeeping: postings, receipts, bank transactions, customers and suppliers. Every endpoint is a POST; auth is HTTP Basic (API client id and secret) plus an api_key field in the request body.
Prerequisiti
Le istruzioni di setup complete sono incluse nel connettore stesso (visibili nello store quando lo selezioni). Le variabili d'ambiente richieste sono:
BUCHHALTUNGSBUTLER_CLIENT_ID, BUCHHALTUNGSBUTLER_CLIENT_SECRET, BUCHHALTUNGSBUTLER_API_KEY
Step 1 — Ottieni le credenziali
Getting credentials — BuchhaltungsButler needs three values, not one.
- In the web app open Einstellungen → API and create an API client. You receive an API client id and an API client secret: these are the HTTP Basic username and password.
- On the same page copy the API key for the client (Mandant) you want to reach. This is a separate value that travels in the JSON body of every request.
- Set
BUCHHALTUNGSBUTLER_CLIENT_ID,BUCHHALTUNGSBUTLER_CLIENT_SECRETandBUCHHALTUNGSBUTLER_API_KEY.
…(continued in the in-app connector instructions)
Step 2 — Installa l'adapter
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
Step 3 — Aggiungi il connettore in Gemini
Gemini CLI legge i server MCP da ~/.gemini/settings.json (o %APPDATA%\gemini\settings.json su Windows). Aggiungi:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Ottieni la tua MCP API key da AnythingMCP → Profilo → MCP API Keys → Nuova Key.
- Salva il file e riavvia
gemini. - Esegui
/mcpnella Gemini CLI —BuchhaltungsButlerdovrebbe essere elencato come disponibile. - Vertex AI Studio: passa
https://cloud.anythingmcp.com/mcpnell'arraytoolsdella richiesta con lo stesso header Bearer.
Tool disponibili
| Tool | What it does |
|---|---|
buchhaltungsbutler_list_postings | Read bookkeeping postings (Buchungen) in a date range, with their account, amount, tax key and the receipt they belong to |
buchhaltungsbutler_list_receipts | Read receipts (Belege) — the scanned or uploaded documents behind the postings — with their date, gross amount, supplier and processing stat |
buchhaltungsbutler_list_transactions | Read bank transactions imported into BuchhaltungsButler, so a posting or an open receipt can be matched against money that actually moved |
buchhaltungsbutler_list_customers | Read the customer master data (Debitoren) with names, customer numbers and the ledger accounts they book to |
buchhaltungsbutler_list_suppliers | Read the supplier master data (Kreditoren) with names, supplier numbers and their ledger accounts, to resolve who an incoming receipt belong |
buchhaltungsbutler_list_accounts | Read the chart of accounts (Sachkonten) available in this client, so a posting can be attributed to the right account number |
FAQ
Gemini 1.5 Pro o 2.x supportano MCP? Sì — Gemini CLI ≥ 0.4 e la Vertex AI tools API accettano connettori MCP httpUrl con header Bearer.
Prossimi passi
Questa guida ti è stata utile?
