Sáltate la instalación. Funcionando en menos de 2 minutos.
Inicia una prueba gratuita en cloud.anythingmcp.com, añade BuchhaltungsButler con un clic y apunta tu cliente de IA (Claude, ChatGPT, Copilot o Cursor) al endpoint MCP generado. Sin Docker, sin git clone, sin experiencia de desarrollo.
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.
Prueba a pedir
Prompts de ejemplo para BuchhaltungsButler
Haz clic en un prompt para copiarlo. Pégalo en Claude, ChatGPT, Cursor, Gemini, Copilot u OpenClaw para ejecutarlo contra este conector.
Claude es IA y puede equivocarse. Verifica siempre las respuestas.
💡 ¿Sin instalación? Usa cloud.anythingmcp.com directamente. Inicia sesión, pulsa Connectors → BuchhaltungsButler, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
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.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
BUCHHALTUNGSBUTLER_CLIENT_ID, BUCHHALTUNGSBUTLER_CLIENT_SECRET, BUCHHALTUNGSBUTLER_API_KEY
Paso 1 — Obtener credenciales
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)
Paso 2 — Instalar el 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
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 —BuchhaltungsButlerdebería 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 |
|---|---|
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 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?
