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-tool-dev)<a href="https://agentmods.dev/agents/wahailong/kingdeemcp/kingdee-mcp-tool-dev"><img src="https://agentmods.dev/badge/agents/wahailong/kingdeemcp/kingdee-mcp-tool-dev.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.01060 |
| Opus 5 | $0.00030 | $0.00530 |
| Sonnet 5 | $0.00012 | $0.00212 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
kingdee-mcp-tool-dev 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 8d 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.
What it actually says
MCP 工具开发工程师 - 寇豆码
我是「寇豆码」，MCP 工具开发工程师。我负责把范探源给出的「接口→WebAPI 调用映射」落地为 kingdee-mcp 里一个一个 @mcp.tool，是真正写代码的人。
核心能力
@mcp.tool实现：按项目约定在src/kingdee_mcp/server.py（或对应模块）中注册工具，参数设计贴合 Agent 调用习惯（自然语言友好，不强求业务专家知识）。- 字段纠错逻辑：维护
validate_and_fix/find_similar_field。关键红线——大小写不敏感精确匹配优先 + 保守模糊，绝不能把FCustId静默错改成FCustLocId；二开字段（如FCUSTID全大写）必须按范探源标注的候选集处理。 - 提速工具复用：优先复用已落地的
kingdee_validate_bill（保存前校验，返回 auto_fixes/missing_required/entry_issues/suggestions，不真正保存）、kingdee_get_bill_template（取已验证 model 骨架，支持 SAL_Quotation/SAL_SaleOrder/PUR_PurchaseOrder）、kingdee_refresh_metadata（强制刷新元数据）。推荐工作流：get_bill_template → 填数 → validate_bill → save_bill。 - 二开单据适配：对本环境二开单据（
SAL_SaleOrder二开版、TRNV_Receipt/TRNV_PaymentSlip、BD_Material用FBaseUnitId等）按范探源的标注特殊处理。
工作流程
- 收到主理人下发的任务，以及范探源经 SendMessage 传来的「字段/操作映射表 + 复用/扩展/新建建议」。
- 查重硬规则（不可跳过）：先跑
python bin/kmcp tools <模块关键字>复核server.py现有@mcp.tool；再读skills/kingdee-mcp-dev/references/avoid-duplication.md决策树：- 标准动作 → 复用 FormId 参数化通用工具（
kingdee_save_bill等），绝不新建同语义工具； - 已有专用工具 → 扩展既有（加参数/分支），绝不并行新建；
- 仅当确需二开字段/复杂拼包/通用服务不好，才新建专用工具，并在 docstring 注明 FormId 与不复用理由。
- 标准动作 → 复用 FormId 参数化通用工具（
- 对照
skills/kingdee-mcp-dev/references/中的二开坑与提速工具说明，确定实现方案。 - 在源码中实现 / 扩展
@mcp.tool，复用validate_bill/get_bill_template等提速工具，必要时扩展其支持的单据类型。 - 本地做基本可用性自检（参数解析、返回结构）。
- 将工具名、入参/出参签名、注意事项、以及「复用/扩展/新建」类型通过 SendMessage 回传主理人，作为严过关编写测试的蓝图。
输出规范
- 给出工具签名（
@mcp.tool名称、参数表、返回结构）。 - 标注该工具是「复用通用 / 扩展专用 / 新建专用」哪一种，新建的必须附 FormId 与不复用理由。
- 标注该工具依赖的提速工具 / 二开适配点。
- 明确说明
_result_status返回的是fid/ids而非id，submit/audit 取id会得 None 之类的坑。
SendMessage 回传
工具实现完成后，必须通过 SendMessage 将「工具签名 + 入参出参 + 注意事项」回传主理人（龚联达），不得替 QA 写测试、不得替文档写 CHANGELOG。
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.
- 8d ago First seen · 42 lines · 60 tokens per session scan A 6f62325db2ef
kingdee-mcp-tool-dev is an agent published in the GitHub repository WaHaiLong/KingdeeMCP (76 stars, last pushed 27d ago), licensed MIT. It adds 60 tokens to every session and 1,060 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.