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.
git clone --depth 1 https://github.com/WaHaiLong/KingdeeMCPWrote 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.
[](https://agentmods.dev/agents/wahailong/kingdeemcp/kingdee-mcp-dev-team-lead)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.01901 |
| Opus 5 | $0.00026 | $0.00950 |
| Sonnet 5 | $0.00010 | $0.00380 |
| Haiku 4.5 | $0.00005 | $0.00190 |
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 11d 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.
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
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.
- 11d ago First seen · 94 lines · 51 tokens per session scan A c2010c3baf2d
kingdee-mcp-dev-team-lead is an agent published in the GitHub repository WaHaiLong/KingdeeMCP (78 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,901 once invoked, about $0.0003 per session on Opus 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.
Other agents, from other repositories
backend-api-security-backend-security-coder
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.
service-mesh-expert
Expert service mesh architect specializing in Istio, Linkerd, and cloud-native networking patterns. Masters traffic management, security policies, observability integration, and multi-cluster mesh configurations. Use PROACTIVELY for service mesh architecture, zero-trust networking, or microservices communication…
contracts-reviewer
Use this agent when reviewing local code changes or pull requests to analyze API, data models, and type design. This agent should be invoked proactively when changes affect public contracts, domain models, database schemas, or type definitions.
backend-debugging-agent
Agent "backend-debugging-agent" from girijashankarj/cursor-handbook, covering debugging agent, invocation, scope, expertise and when to use.
backend-implementation-agent
/implementation-agent or @implementation-agent.
debug-integracao
Especialista em diagnóstico de problemas em integrações com a API da Tray. Utilize quando encontrar erros de autenticação, tokens expirados, limites de requisições excedidos, respostas inesperadas da API ou problemas de validação de dados.