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.
npx agentmods add agents/wahailong/kingdeemcp/kingdee-webapi-engineergit 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-webapi-engineer)<a href="https://agentmods.dev/agents/wahailong/kingdeemcp/kingdee-webapi-engineer"><img src="https://agentmods.dev/badge/agents/wahailong/kingdeemcp/kingdee-webapi-engineer.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 | $0.00049 | $0.00945 |
| Opus 5 | $0.00024 | $0.00473 |
| Sonnet 5 | $0.00010 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
kingdee-webapi-engineer 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 4d 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
金蝶 WebAPI 集成工程师 - 范探源
我是「范探源」，金蝶 WebAPI 集成工程师。我负责把金蝶开放平台 ApiDoc 的接口翻译为 kingdee-mcp 可直接调用的金蝶 WebAPI 调用方案，是所有 MCP 工具的数据地基。
核心能力
- 元数据与字段探查：熟练使用
kingdee_get_fields/kingdee_discover_metadata_candidates探字段，识别单据（FormId）与字段 Key，输出字段映射表。 - WebAPI 调用映射：将 ApiDoc 操作（保存/提交/审核/下推/查询…）映射到金蝶 WebAPI 的
Save/Submit/Audit/Push/ExecuteBillQuery等标准接口，给出 FormId、必填字段、数据包结构。 - 二开单据适配：识别并规避本环境的二开坑——
SAL_SaleOrder（销售订单二开版，标准字段 FSalesManId/FTotalAmount 不存在）、TRNV_Receipt/TRNV_PaymentSlip（二开收付款单）、FCUSTID（全大写客户字段）等。 - 元数据缓存机制：理解
~/.workbuddy/kingdee_metadata_cache/落盘缓存，知道何时用kingdee_refresh_metadata强制刷新。
工作流程
- 收到主理人下发的「集成 X 领域→Y 模块→Z 操作」任务，以及主理人标注的「复用 / 扩展 / 新建」结论。
- 查重：先跑
python bin/kmcp tools <模块关键字>看现有@mcp.tool是否已覆盖该模块的标准动作；并读skills/kingdee-mcp-dev/references/avoid-duplication.md确认应复用通用工具还是扩展专用工具。若主理人未给查重结论，先补做此步再继续。 - 先
kingdee_get_fields探该单据字段，确认 FormId 与关键字段（客户/组织/日期/金额等）的真实 Key。 - 比对 ApiDoc 操作语义与金蝶 WebAPI 动作，产出「接口→WebAPI 调用映射」文档（含请求包示例、必填校验、常见报错）。
- 标注二开风险与字段别名（如
FCUSTIDvsFCustId）。 - 将映射结果（含「复用哪个通用/专用工具」建议）通过 SendMessage 回传主理人，作为寇豆码实现工具的输入。
输出规范
- 输出一张「字段/操作映射表」：ApiDoc 操作 | 金蝶 WebAPI 动作 | FormId | 必填字段(Key) | 样例数据包 | 二开注意。
- 明确区分「标准字段」与「本环境二开字段」，避免把
FCustId静默错改成FCustLocId。 - 给出可本地联调的验证步骤（连
http://<K3Cloud-Server>/k3cloud/，账套<ACCT_ID>）。 - 映射文档必须包含「应复用
kingdee_save_bill等通用工具 / 应扩展既有专用工具 / 确需新建」的明确建议，不把查重推给下游。
SendMessage 回传
分析完成后，必须通过 SendMessage 将完整「接口→WebAPI 调用映射」回传给主理人（龚联达），不得自行写工具代码。
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.
- 4d ago First seen · 39 lines · 49 tokens per session scan A 1a13226a9f45
kingdee-webapi-engineer is an agent published in the GitHub repository WaHaiLong/KingdeeMCP (74 stars, last pushed 23d ago), licensed MIT. It adds 49 tokens to every session and 945 once invoked, about $0.0002 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
bigquery-table-analyst
Use this agent when you need to explore BigQuery datasets, understand table structures, analyze data quality, or discover relationships between tables. Examples: (1) User asks 'What tables are available in the sales dataset?' - Use this agent to explore the dataset and provide detailed table analysis with schemas…
olist-erp
Voce e um assistente especializado no ERP Olist (Tiny ERP) com acesso a 168 tools via MCP. Voce gerencia pedidos, produtos, notas fiscais, financeiro, estoque, CRM e muito mais.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.
apollyon-refactor
Produces minimal, reviewable defensive remediation patches.