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 ERPNext，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。
Summary
ERPNext / Frappe: read and write any DocType — customers, sales orders, invoices, items, stock and leads — with Frappe's filter syntax, plus a generic resource escape hatch. Token auth against your own instance.
试试这样问
ERPNext 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 → ERPNext、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
ERPNext + Gemini
ERPNext / Frappe: read and write any DocType — customers, sales orders, invoices, items, stock and leads — with Frappe's filter syntax, plus a generic resource escape hatch. Token auth against your own instance.
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:
ERPNEXT_URL, ERPNEXT_API_KEY, ERPNEXT_API_SECRET
步骤 1 — 获取凭证
Getting a key
- In ERPNext open the user you want the agent to act as → Settings → API Access → Generate Keys. You receive an API key and an API secret; the secret is shown once.
- Set
ERPNEXT_URLto your instance root (no trailing slash),ERPNEXT_API_KEYandERPNEXT_API_SECRET.
The Authorization header is token key:secret — lower-case token, the two values joined by a colon. Not Bearer, not Basic. This is the single most common reason a correct ERPNext key 401s.
…(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
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—ERPNext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 |
|---|---|
erpnext_get_logged_user | Read which user the API key belongs to |
erpnext_list_documents | List documents of any DocType with Frappe filters |
erpnext_get_document | Read one document of any DocType in full by its name (ERPNext's primary key), including its child tables |
erpnext_count_documents | Count the documents of a DocType matching a filter, without transferring them |
erpnext_get_doctype_meta | Describe a DocType: every field with its type, label, options and whether it is required |
erpnext_list_customers | List customers with their name, group, territory, currency and default payment terms |
erpnext_list_sales_orders | List sales orders with their customer, date, delivery date, status and grand total |
erpnext_list_sales_invoices | List sales invoices with their customer, posting date, due date, status and outstanding amount — the answer to 'what is still unpaid' |
erpnext_list_items | List items from the catalogue with their code, name, group, stock UOM and default rate |
erpnext_list_stock_balance | Read per-warehouse stock: actual, reserved and projected quantity per item |
erpnext_create_document | Create a document of any DocType |
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
这份指南对你有帮助吗?
