Skip to main content

金蝶开发者社区搜索 MCP Server

这是一个 Model Context Protocol (MCP) 服务器,用于搜索金蝶开发者社区的知识库。

功能特性

  • 🔍 根据关键字搜索金蝶开发者社区知识库
  • 📊 以表格形式展示搜索结果
  • 📈 显示统计信息(活动数、SDK数、资源数等)
  • 🔗 提供知识库链接
  • 📄 显示高亮摘要内容

安装

  1. 确保已安装 Python 3.8 或更高版本
  2. 安装依赖:
pip install -r requirements.txt

使用方法

作为 MCP Server 运行

  1. 启动服务器:
python -m kingdee_search_server

或

python src/kingdee_search_server.py
  1. 服务器通过 stdio 与 MCP 客户端通信

工具说明

search_kingdee_developer

搜索金蝶开发者社区的知识库。

  • 参数:

    • keyword (必需): 搜索关键字,例如:"自定义API"、"Java插件"等
    • pageNo (可选): 页码,从1开始,默认为1
    • pageSize (可选): 每页返回的结果数量,默认为20
  • 示例:

{
  "keyword": "自定义API",
  "pageNo": 1,
  "pageSize": 20
}
  • 返回:
    • 统计信息(活动数、SDK数、资源数、开发者数、OpenAPI数)
    • 搜索结果列表(标题、浏览量、ID、摘要、链接)

MCP 服务配置(机器可读)

以下 JSON 片段用于 MCP 广场/注册表自动解析(包含标准 $schema):

{
  "$schema": "https://modelcontextprotocol.io/schemas/registry/manifest.schema.json",
  "name": "kingdee-search-server",
  "description": "搜索金蝶开发者社区知识库的 MCP 服务器",
  "version": "1.0.0",
  "license": "MIT",
  "repository": "https://github.com/qiliang517/kingdee-search-mcp",
  "servers": [
    {
      "type": "stdio",
      "command": "python",
      "args": ["-m", "kingdee_search_server"],
      "env": {},
      "runtime": "python"
    }
  ],
  "tools": [
    {
      "name": "search_kingdee_developer",
      "description": "根据关键字搜索金蝶开发者社区知识库,返回格式化表格。",
      "inputSchema": {
        "type": "object",
        "properties": {
          "keyword": {
            "type": "string",
            "description": "搜索关键字,例如:'自定义API'、'Java插件'等"
          },
          "pageNo": {
            "type": "integer",
            "description": "页码,从1开始,默认为1",
            "default": 1
          },
          "pageSize": {
            "type": "integer",
            "description": "每页返回的结果数量,默认为20",
            "default": 20
          }
        },
        "required": ["keyword"]
      }
    }
  ]
}

API 说明

服务器调用以下 API:

https://dev.kingdee.com/prod-api/kd/ecos/node/search?type=developer&keyword={keyword}&pageNo={pageNo}&pageSize={pageSize}

项目结构

mcp-server/
├── src/
│   └── kingdee_search_server.py  # MCP 服务器主程序
├── requirements.txt              # Python 依赖
├── README.md                     # 本文件
└── 其他发布与部署文件

部署

发布到 PyPI(简要)

pip install build twine
python -m build
twine upload dist/*

部署到 MCP 广场

请参考 DEPLOY.md 获取完整步骤(魔搭 MCP 广场、PyPI、GitHub、本地部署)。

许可证

MIT

Metadata

Release files for kingdee-search-mcp 1.0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for kingdee-search-mcp 1.0.0
File Interpreter ABI Platform
kingdee_search_mcp-1.0.0-py3-none-any.whl Python 3 none any Details

Release files / kingdee_search_mcp-1.0.0-py3-none-any.whl

Download URL kingdee_search_mcp-1.0.0-py3-none-any.whl
Size 3.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
15af0527387a3969ed70ad857d225f71b2145193ba75a9bfcccc94893679e250
BLAKE2b-256 checksum
How to use checksums
c12ca9658d680183d2e340101dbbcdbad6b211f4722a9e920173ef958155b454
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.10.0rc2

Security for kingdee-search-mcp 1.0.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.0.0 This release

1 release file No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page