No install? Use cloud.anythingmcp.com directly.
Sign in, install the SAP Business One in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Drive SAP Business One ERP (popular Mittelstand SMB target in DACH) from any AI agent: business partners, items, sales orders, A/R invoices, quotations, deliveries. Service Layer OData v4. Session-cookie auth via /Login.
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → SAP Business One、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
SAP Business One + Gemini
Drive SAP Business One ERP (popular Mittelstand SMB target in DACH) from any AI agent: business partners, items, sales orders, A/R invoices, quotations, deliveries. Service Layer OData v4. Session-cookie auth via /Login.
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:
SAP_B1_HOST, SAP_B1_PORT, SAP_B1_COMPANY_DB, SAP_B1_USERNAME, SAP_B1_PASSWORD
步骤 1 — 获取凭证
Setup:
- Identify your Service Layer host (typically the same machine that runs HANA + SAP B1). Default HTTPS port is
50000. - Create or pick a B1 user that has API access for the company database you want to expose.
- Find the
CompanyDBname in Choose Company dialog of the B1 client (looks likeSBODEMOGB). - Set the five env vars below. The adapter logs in once per session (~25 min TTL) and re-uses the
B1SESSIONcookie.
OData: this adapter targets the v2 / OData v4 Service Layer endpoint at /b1s/v2/. Older /b1s/v1/ (OData v3) deployments are not covered — upgrade to FP 2405+ first.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
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",
"headers": { "Authorization": "Bearer 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—SAP Business One应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
b1_list_business_partners | List business partners (customers, suppliers, leads) |
b1_get_business_partner | Get one business partner by CardCode |
b1_list_items | List inventory items (articles) |
b1_get_item | Get one item by ItemCode |
b1_list_orders | List sales orders |
b1_get_order | Get one sales order by DocEntry (integer primary key) |
b1_create_order | Create a new sales order |
b1_list_invoices | List A/R invoices |
b1_get_invoice | Get one A/R invoice by DocEntry |
b1_list_quotations | List sales quotations |
b1_list_delivery_notes | List delivery notes (outgoing goods movements) |
b1_get_company_info | Sanity check: returns company metadata (admin info) |
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 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对您有帮助吗?