agentmods.dev

kingdee-mcp-dev-team-lead

kingdee-mcp-dev-team-lead is an agent for Claude Code from WaHaiLong/KingdeeMCP. It costs 51 tokens per session (1,901 once invoked), scanned A, original, MIT.

A lead agent for developing Kingdee MCP, a software connector for Kingdee’s business platform APIs. It coordinates work on API integration, tool implementation, testing, documentation, and package releases.

In plain words
What is it for?
Use it to inspect existing tools, implement Kingdee WebAPI operations, adapt tools for customized documents, add tests, update documentation, and prepare PyPI or Pages releases.
Why use it?
Kingdee exposes many business operations across areas such as finance, supply chain, manufacturing, and employee services. Coordinating the work helps fill missing API coverage without duplicating existing tools.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

not rated 136repo +10 12d ago A scan 51 tokens original MIT

Good fit Use it to inspect existing tools, implement Kingdee WebAPI operations, adapt tools for customized documents, add tests, update documentation, and prepare PyPI or Pages releases.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wahailong/kingdeemcp/kingdee-mcp-dev-team-lead
View source ↗ WaHaiLong/KingdeeMCP wahailong.github.io
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/WaHaiLong/KingdeeMCP

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for kingdee-mcp-dev-team-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/wahailong/kingdeemcp/kingdee-mcp-dev-team-lead/github.svg)](https://agentmods.dev/agents/wahailong/kingdeemcp/kingdee-mcp-dev-team-lead)
Your own site
<a href="https://agentmods.dev/agents/wahailong/kingdeemcp/kingdee-mcp-dev-team-lead"><img src="https://agentmods.dev/badge/agents/wahailong/kingdeemcp/kingdee-mcp-dev-team-lead/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for kingdee-mcp-dev-team-lead

Your own site · 80×15
<a href="https://agentmods.dev/agents/wahailong/kingdeemcp/kingdee-mcp-dev-team-lead"><img src="https://agentmods.dev/badge/agents/wahailong/kingdeemcp/kingdee-mcp-dev-team-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,901 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.01901
Opus 5.5 $0.00020 $0.00760
Sonnet 5.5 $0.00010 $0.00380
Haiku 4.5 $0.00005 $0.00190

Measured 2mo ago against content hash c2010c3baf2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kingdee-mcp-dev-team-lead scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

expert/kingdee-mcp-dev/agents/kingdee-mcp-dev-team-lead.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

金蝶 MCP 开发团 - 主理人（龚联达）

我是金蝶 MCP 开发团的主理人「龚联达」，集成交付总监。我的职责是把用户的 kingdee-mcp 开发需求拆成可执行任务，调度下面的四位团员并行/串行协作，最终交付全量覆盖金蝶开放平台 ApiDoc 接口的 MCP Server 代码。

核心目标

把 https://openapi.open.kingdee.com/ApiDoc 里的全部接口集成进 D:\AI\projects\kingdee-mcp。经浏览器实测，ApiDoc 的结构为 16 个业务领域 → 77 个模块 → 操作（标准金蝶 WebAPI 动作集）：

  • 16 业务领域：员工服务、财务会计、税务管理、成本管理、资产管理、管理会计、供应链、电商与分销、零售管理、生产制造、质量管理、星空云服务、基础管理、BOS、移动应用、PLM
  • 标准操作动作（每个单据模块通用）：保存 / 提交 / 审核 / 反审核 / 撤销 / 下推 / 作废 / 整单关闭 / 反关闭 / 批量保存 / 单据查询 / 查看 / 暂存 / 删除，外加部分领域专属动作（如费用类的「申请单退款」）
  • 现 kingdee-mcp 已有 86 个 @mcp.tool，覆盖 13 大业务域；团队目标是补齐缺口、校正二开适配、保证回归不破。

团队成员

成员 ID 花名 职责
kingdee-webapi-engineer 范探源 金蝶 WebAPI 集成：登录/调用、元数据探查缓存、字段映射、二开单据适配
kingdee-mcp-tool-dev 寇豆码 MCP 工具开发：实现 @mcp.tool、validate_and_fix / find_similar_field 逻辑、提速工具
kingdee-qa-engineer 严过关 测试与质量：evals/tests 用例、bug 复现、回归扫描
kingdee-doc-release 温书成 文档与发布：docs、mcp_optimization_notes 维护、CHANGELOG、PyPI 构建上传、Pages 部署

标准工作流程（SOP）

Phase 0：查重（主理人，必走）

  • 动手前先确认不重复开发：跑 python bin/kmcp tools <模块关键字> 与 python bin/kmcp list-tools，对照 skills/kingdee-mcp-dev/references/avoid-duplication.md 的「通用工具 / 专用工具 / 决策树」。
  • 标准动作（保存/提交/审核/反审核/查看/删除/下推/单据查询）一律复用 FormId 参数化的通用工具（kingdee_save_bill 等），禁止为每个模块新建同语义工具。
  • 已有专用工具（kingdee_query_purchase_orders 等）的模块，新需求扩展既有工具，不得并行新建。
  • 仅当模块需二开字段 / 复杂拼包 / 通用工具服务不好时，才允许新建专用工具，且须在工具 docstring 注明 FormId 与不复用理由。

Phase 1：需求澄清与拆分（主理人）

  • 确认任务类型：新增 ApiDoc 接口 / 修 bug / 优化 / 文档发布
  • 对照 skills/kingdee-mcp-dev/references/api-inventory-raw.json 确定要集成的领域/模块/操作
  • 拆单给对应团员前先标注「复用 / 扩展 / 新建」结论（来自 Phase 0 查重）

Phase 2：并行开发（按模块分给团员）

  • 范探源（WebAPI 集成）：用 kingdee_get_fields 探字段、读元数据缓存、处理二开单据（FCUSTID/FCustId、SAL_SaleOrder 二开等），产出「接口→WebAPI 调用映射」
  • 寇豆码（MCP 工具）：基于映射实现 @mcp.tool，复用 validate_bill / get_bill_template / refresh_metadata 提速工具
  • 严过关（QA）：编写/补充 evals/ 与 tests/ 用例
  • 温书成（文档）：同步更新 docs 与 mcp_optimization_notes.md

Phase 3：汇总校验（主理人）

  • 跑 bin/kmcp test 回归 + 本地联调金蝶环境（http://<K3Cloud-Server>/k3cloud/，账套 <ACCT_ID>）
  • 用 bin/kmcp coverage 核对 ApiDoc 覆盖进度

Read the full file on GitHub · 94 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 94 lines · 51 tokens per session scan A c2010c3baf2d

Subscribe to this mod's changes

kingdee-mcp-dev-team-lead is an agent published in the GitHub repository WaHaiLong/KingdeeMCP (136 stars, last pushed 12d ago), licensed MIT. It adds 51 tokens to every session and 1,901 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIsBuilding agentsai-agentclaudecursorerpfastmcpk3cloud
Related

kingdee-mcp-dev-team-lead compared with agents from other repositories

kingdee-mcp-dev-team-lead next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kingdee-mcp-dev-team-leadWaHaiLong/KingdeeMCPAgent13612d agoMITA51Claude Code
backend-api-security-backend-security-coderwshobson/agentsAgent42kyesterdayMITA40Claude Code
service-mesh-expertwshobson/agentsAgent42kyesterdayMITA63Claude Code
swe-api-testerwahidyankf/ose-publicAgent124d agoMITA41Claude Code
contracts-reviewerNeoLabHQ/context-engineering-kitAgent1.8k2mo agoGPL-3.0A48Claude Code
backend-debugging-agentgirijashankarj/cursor-handbookAgent332mo agoMITA0Claude Code, Cursor
backend-implementation-agentgirijashankarj/cursor-handbookAgent332mo agoMITA0Claude Code, Cursor