Skip to main content
Glama

ERPNext MCP 服务器

用于 ERPNext 集成的模型上下文协议服务器

这是一个基于 TypeScript 的 MCP 服务器,提供与 ERPNext/Frappe API 的集成。它使 AI 助手能够通过模型上下文协议 (MCP) 与 ERPNext 数据和功能进行交互。

特征

资源

  • 通过erpnext://{doctype}/{name} URI 访问 ERPNext 文档

  • 用于结构化数据访问的 JSON 格式

工具

  • authenticate_erpnext - 使用用户名和密码向 ERPNext 进行身份验证

  • get_documents - 获取特定文档类型的文档列表

  • create_document - 在 ERPNext 中创建新文档

  • update_document - 更新 ERPNext 中的现有文档

  • run_report - 运行 ERPNext 报告

  • get_doctype_fields - 获取特定 DocType 的字段列表

  • get_doctypes - 获取所有可用 DocType 的列表

配置

服务器需要以下环境变量:

  • ERPNEXT_URL - ERPNext 实例的基本 URL

  • ERPNEXT_API_KEY (可选)- 用于身份验证的 API 密钥

  • ERPNEXT_API_SECRET (可选)- 用于身份验证的 API 密钥

发展

安装依赖项:

npm install

构建服务器:

npm run build

对于使用自动重建的开发:

npm run watch

安装

要与 Claude Desktop 一起使用,请添加服务器配置:

在 MacOS 上: ~/Library/Application Support/Claude/claude_desktop_config.json在 Windows 上: %APPDATA%/Claude/claude_desktop_config.json

{ "mcpServers": { "erpnext": { "command": "node", "args": ["/path/to/erpnext-server/build/index.js"], "env": { "ERPNEXT_URL": "http://your-erpnext-instance.com", "ERPNEXT_API_KEY": "your-api-key", "ERPNEXT_API_SECRET": "your-api-secret" } } } }

要在 VSCode 中与 Claude 一起使用,请将服务器配置添加到:

在 MacOS 上: ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json在 Windows 上: %APPDATA%/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

调试

由于 MCP 服务器通过 stdio 进行通信,调试起来可能比较困难。我们推荐使用MCP Inspector ,它以包脚本的形式提供:

npm run inspector

检查器将提供一个 URL 来访问浏览器中的调试工具。

使用示例

验证

<use_mcp_tool> <server_name>erpnext</server_name> <tool_name>authenticate_erpnext</tool_name> <arguments> { "username": "your-username", "password": "your-password" } </arguments> </use_mcp_tool>

获取客户列表

<use_mcp_tool> <server_name>erpnext</server_name> <tool_name>get_documents</tool_name> <arguments> { "doctype": "Customer" } </arguments> </use_mcp_tool>

获取客户详细信息

<access_mcp_resource> <server_name>erpnext</server_name> <uri>erpnext://Customer/CUSTOMER001</uri> </access_mcp_resource>

创建新项目

<use_mcp_tool> <server_name>erpnext</server_name> <tool_name>create_document</tool_name> <arguments> { "doctype": "Item", "data": { "item_code": "ITEM001", "item_name": "Test Item", "item_group": "Products", "stock_uom": "Nos" } } </arguments> </use_mcp_tool>

获取项目字段

<use_mcp_tool> <server_name>erpnext</server_name> <tool_name>get_doctype_fields</tool_name> <arguments> { "doctype": "Item" } </arguments> </use_mcp_tool>
-
security - not tested
A
license - permissive license
-
quality - not tested

Related MCP Servers

  • -
    security
    F
    license
    -
    quality
    This is an MCP server that facilitates building tools for interacting with various APIs and workflows, supporting Python-based development with potential for customizable prompts and user configurations.
    Last updated -
  • -
    security
    -
    license
    -
    quality
    A TypeScript-based server that enables AI assistants to interact with ERPNext/Frappe systems through the Model Context Protocol, allowing access to documents, creation/updating of records, and running reports.
    Last updated -
    36
    MIT License
    • Apple
  • -
    security
    A
    license
    -
    quality
    An MCP server that enables AI platforms to interact with YepCode's infrastructure, allowing LLM-generated scripts to run on YepCode and turning YepCode processes into powerful tools that AI assistants can use directly.
    Last updated -
    126
    39
    MIT License
    • Linux
    • Apple
  • A
    security
    F
    license
    A
    quality
    An all-in-one Model Context Protocol (MCP) server that connects your coding AI to numerous databases, data warehouses, data pipelines, and cloud services, streamlining development workflow through seamless integrations.
    Last updated -
    3
    • Apple
    • Linux

View all related MCP servers

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rakeshgangwar/erpnext-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server