跳过安装。2 分钟内即可运行。
在 cloud.anythingmcp.com 开始免费试用，一键添加 sevDesk，然后将你的 AI 客户端（Claude、ChatGPT、Copilot 或 Cursor）指向生成的 MCP 端点。无需 Docker，无需 git clone，无需任何工程经验。
摘要
面向德国中小企业和自由职业者的 sevDesk 云端记账：联系人、发票、凭证 (Belege)、订单、部件和银行账户。REST API v1，API 密钥身份验证：密钥直接放在 Authorization 标头中，不带 Bearer 前缀。
试试这样问
sevDesk 的示例提示
点击任意提示即可复制，然后粘贴到 Claude、ChatGPT、Cursor、Gemini、Copilot 或 OpenClaw 中，在该连接器上运行。
Claude 是 AI，可能会出错。请核对回答。
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → sevDesk、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
sevDesk + Gemini
面向德国中小企业和自由职业者的 sevDesk 云端记账：联系人、发票、凭证 (Belege)、订单、部件和银行账户。REST API v1，API 密钥身份验证：密钥直接放在 Authorization 标头中，不带 Bearer 前缀。
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
SEVDESK_API_KEY
步骤 1 — 获取凭证
Getting a key
- Sign in to sevDesk and open Einstellungen → Benutzer → (your user) → API-Token.
- Copy the token into
SEVDESK_API_KEY. It belongs to one user in one client (Mandant) and inherits that user's permissions — create a dedicated API user with read rights if the agent should not be able to write.
The Authorization header has no scheme. sevDesk expects the raw token (Authorization: abc123…), not Bearer abc123…. This adapter sends it that way; if you build a custom connector against sevDesk by hand, that is the single most common reason for a 401.
…(continued in the in-app connector instructions)
步骤 2 — 安装 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
步骤 3 — 在 Gemini 中添加连接器
你的服务器 URL： 在 AnythingMCP 中打开 MCP Servers → 此连接器所在的服务器，复制它的 URL（
https://cloud.anythingmcp.com/mcp/…）。本指南中出现YOUR_SERVER_ID的地方都用它替换。
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
"headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—sevDesk应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID传入请求的tools数组,使用相同的X-API-Key请求头。
可用工具
| Tool | What it does |
|---|---|
sevdesk_list_users | List the sevDesk users in this client, with their names and e-mail addresses |
sevdesk_list_contacts | List contacts (customers, suppliers, partners) |
sevdesk_get_contact | Read one contact by its numeric sevDesk id, with its category, customer number, tax settings and default payment terms |
sevdesk_list_invoices | List outgoing invoices, newest first |
sevdesk_get_invoice_positions | Read the line items (Positionen) of one invoice: article, quantity, unit price, tax rate and the resulting net and gross sums |
sevdesk_list_vouchers | List vouchers (Belege) — incoming supplier invoices and receipts |
sevdesk_list_orders | List orders and quotations (Aufträge und Angebote) |
sevdesk_list_parts | List parts (Artikel) from the sevDesk product catalogue with their price, stock level, unit and tax rate |
sevdesk_list_check_accounts | List the bank and cash accounts (Kassen und Bankkonten) configured in sevDesk, with their current balance and import type |
sevdesk_list_transactions | List bank transactions on one check account, so unpaid invoices can be matched against money that actually arrived |
sevdesk_create_contact | Create a new contact |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带自定义请求头的 MCP httpUrl 连接器。
下一步
这份指南对你有帮助吗?
