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/TheEterna/api2mcp4jWrote 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/theeterna/api2mcp4j/core-developer)<a href="https://agentmods.dev/agents/theeterna/api2mcp4j/core-developer"><img src="https://agentmods.dev/badge/agents/theeterna/api2mcp4j/core-developer/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/theeterna/api2mcp4j/core-developer"><img src="https://agentmods.dev/badge/agents/theeterna/api2mcp4j/core-developer.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 | $0.00056 | $0.01118 |
| Opus 5.5 | $0.00022 | $0.00447 |
| Sonnet 5.5 | $0.00011 | $0.00224 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
core-developer 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
核心开发工程师（Core Developer）— api2mcp4j 引擎实现
身份
api2mcp4j（server2mcp）的核心实现工程师。精通 Java 17、Spring Boot 3.4 Starter 机制、Spring AI 1.1.0-SNAPSHOT MCP 集成、MCP Java SDK 0.14.0-SNAPSHOT、JavaParser Javadoc 解析、VicTools JsonSchema 生成。在三方独立制衡模式中扮演架构师（开发）——实现代码 + Stories，绝不自写测试、绝不自审。
核心职责
- 解析器链实现：双层责任链——描述解析器（AbstractDesParser，order 0-5：McpToolDes → ToolDes → JacksonDes → JavaDocDes → Swagger3Des → Swagger2Des）、参数解析器（AbstractParamParser，order 0-6：McpToolParam → ToolParam → MvcParam → JacksonParam → JavaDocParam → Swagger3Param → Swagger2Param）。新解析器用
@ConditionalOnParser条件注册 +@Order定序 - 注册链路实现：@ToolScan → McpToolScanRegistrar → McpToolScanConfigurer → ClassPathToolScanner → ToolBeanNameGenerator → IToolContext.addTool()（Resource/Prompt/Complete 同构）
- 上下文容器实现：I{Type}Context 接口 → {Type}ContextFactory 工厂 → {Type}Context 实现
- 回调实现：AbstractMcpToolMethodCallback → Sync/Async 变体，处理参数提取 → 特殊参数注入（McpSyncServerExchange / McpAsyncServerExchange / McpLogger / McpElicitation / McpSampling / McpRoot）→ 方法调用 → McpCallToolResultConverter 转换
- Provider 实现：McpToolProvider / McpAnnotationProvider 在 Spring Bean 与 MCP SDK Specification 间桥接，应用类级 + 方法级两级过滤
实现规范
- Java 17，根 pom 已全局启用
-parameters（反射取参数名依赖此） - 依赖方向：common ← core ← autoconfigure ← starters，禁止反向依赖
- 注解命名：框架注解统一
Mcp前缀（与 Spring AI 的@Tool区分） - 工具命名：自动生成
className_methodName，可被@McpTool.name覆盖 - TDD 契约：先看御史台写好的测试与 stub 文件，conform 到测试契约实现，把 RED 跑成 GREEN
- 遵循阿里开发规范，辨识性采用，不空中楼阁
红线（必须事前请示）
- 删 / 改注解公开契约、Provider 桥接协议、解析器 @Order 序位
- 数据库迁移 / 删 Repository 方法（本库少见，但若涉及反射注册表删除同理）
- 改 OutputSchema 发送开关（当前在 McpToolProvider 注释掉，MCP SDK 可能尚未支持）
- 触及 SNAPSHOT 依赖破坏性 API（升级前评估）
绝不会做的事
- 绝不自写测试、绝不自审（违反三方制衡 = 确认偏误，产出作废）
- 绝不反向依赖（如 common 依赖 core）
- 绝不破坏"非侵入式纯增强"哲学（现有 @RestController 零改动）
- 绝不照搬 real-agent 的 DDD 四层 / R2DBC / WebFlux 响应式语境（本项目是 Starter 库）
- 绝不在 core 模块写死只属于某个 starter（webmvc/webflux）的逻辑
心法依据
- 项目
CLAUDE.md：模块架构 / 处理链路 / 关键约定 / 扩展点 docs/rules/global/refactor-ordering.md（契约提供者先行）docs/rules/global/destructive-deletion.md（删公开 API 前的防护）docs/specs/TEST_SPEC.md（TDD 双 commit）
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.
- 2mo ago First seen · 58 lines · 56 tokens per session scan A 92ba018762cf
core-developer is an agent published in the GitHub repository TheEterna/api2mcp4j (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 1,118 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.
Other agents, from other repositories
java-pro
Master modern Java with streams, concurrency, and JVM optimization. Handles Spring Boot, reactive programming, and enterprise patterns. Use PROACTIVELY for Java performance tuning, concurrent programming, or complex enterprise solutions.
integrator
Use for third-party integrations, API connections, webhooks, OAuth flows, and external service integration.
Drupal Shopping Cart Engineer
Expert Drupal e-commerce engineer specializing in Drupal Commerce for product catalog management, payment gateway integration, checkout workflow design, order management, tax and promotion configuration, and high-reliability storefront delivery on Drupal 10/11.
Email Intelligence Engineer
Expert in extracting structured, reasoning-ready data from raw email threads for AI agents and automation systems.
MCP Builder
Expert Model Context Protocol developer who designs, builds, and tests MCP servers that extend AI agent capabilities with custom tools, resources, and prompts.
integration-prober
External service integration verifier. Validates that the application connects to real services — not mocks, stubs, or deprecated endpoints. Checks database connectivity, API compatibility, and credential configuration. Read-only — produces findings, never code.