{"name":"io.github.mybolide/mcp-probe-kit","slug":"mybolide-mcp-probe-kit","title":null,"description":"Spec-driven dev workflow MCP: start_* orchestration, memory, GitNexus, quality gates.","url":"https://mcp.market/server/mybolide-mcp-probe-kit","rating":null,"grade":"A","score":92,"certified":false,"status":"active","category":"other","tags":[],"presence":{"score":42,"stars":41,"forks":5,"downloads_week":156,"last_push_at":"2026-11-04T05:50:48.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"npm","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/mybolide/mcp-probe-kit","website":null,"version":"4.0.0","remotes":[],"packages":[{"registryType":"npm","identifier":"mcp-probe-kit","version":"4.0.0","transport":{"type":"stdio"}}],"tools":[{"name":"add_feature","description":"原子规格生成工具：根据已经确定的 feature_name、description、spec_layout 和可选 subspecs，返回 flat 或 parent-child 规格模板与落盘计划。它不负责判断需求复杂度，也不是复杂功能的首个入口。新功能、跨模块升级或布局未确定时必须先调用 start_feature；通常仅按 start_feature 返回的 delegated plan 调用本工具。","write_action":false,"price_micros":0,"input_schema":null},{"name":"architecture","description":"独立架构领域能力，使用 ARC-8 完成架构评估、设计、校验和漂移检查。可直接调用，也可由功能、Bug 或重构流程按需组合；MCP 负责方法、门禁与结构化证据，不替 Agent 声称绝对最优架构。","write_action":false,"price_micros":0,"input_schema":null},{"name":"ask_user","description":"当 AI 需要更多信息、遇到不确定因素时使用。向用户提问工具，AI 可主动向用户提问；支持单个或多个问题、提供选项、标注重要性；可在任何时候使用","write_action":false,"price_micros":0,"input_schema":null},{"name":"check_spec","description":"校验已落盘的功能规格（docs/specs/<feature_name>/requirements|design|tasks.md）是否完整：检测残留 [填写] 占位、缺失章节、缺 FR/验收标准、FR 未进覆盖矩阵。写完规格后、进入实现前调用；未通过按报告补全后重跑。","write_action":false,"price_micros":0,"input_schema":null},{"name":"code_insight","description":"当用户需要基于代码图谱分析调用链、上下文和影响面时使用。默认桥接 GitNexus，支持 query/context/impact 模式；不可用时自动降级并返回原因","write_action":false,"price_micros":0,"input_schema":null},{"name":"code_review","description":"当用户需要审查代码、真实 Git diff 或托管 Plan 的交付一致性时使用。MCP 可确定性收集 changed files、Plan 声明范围、产物、测试、公共契约、架构和 revision 证据；代码语义问题仍由 Agent 审查，不伪装成静态扫描器","write_action":false,"price_micros":0,"input_schema":null},{"name":"converge","description":"按 Delegated Plan 自己声明的证据和质量闸门关闭计划。任一未完成步骤、未决事项、必需证据或验收结果缺失都会拒绝收敛；除 requirements 外，证据只有摘要但没有 reference/revision 也不算可复核证据。调用参数只能增加证据要求，不能削弱 Plan。","write_action":false,"price_micros":0,"input_schema":null},{"name":"delete_memory_asset","description":"按 asset_id 从共享记忆库删除一条未参与 supersede 链的资产。适用于错误、重复或无价值沉淀；已有关联关系的资产必须改用 update_memory_asset 设置 retracted 并保留 evidence。","write_action":true,"price_micros":0,"input_schema":null},{"name":"estimate","description":"当用户需要估算开发工作量、评估任务时间时使用。估算开发工作量，输出故事点、时间范围（乐观/正常/悲观）、风险点","write_action":false,"price_micros":0,"input_schema":null},{"name":"fix_bug","description":"当用户需要找问题、修 bug、排查异常时使用。指南型 SRC-8（TBP-inspired）：注入真因工作表与门禁，由 Agent 完成 rootCauseAnalysis 并修复；MCP 不自动修 Bug","write_action":false,"price_micros":0,"input_schema":null},{"name":"gencommit","description":"当用户需要生成 Git commit 消息时使用。返回 Conventional Commits 规范说明、步骤、输出模板和示例，供 AI 根据变更内容生成最终 commit message。它不直接代写最终消息，也不应被判定为空结果","write_action":false,"price_micros":0,"input_schema":null},{"name":"gentest","description":"当用户需要为代码生成单元测试时使用。指南型工具：注入 code/file_path 与测试清单，由 Agent 生成完整测试代码；MCP 不自动生成或运行测试","write_action":false,"price_micros":0,"input_schema":null},{"name":"git_work_report","description":"基于 Git diff 分析生成工作报告（日报/周期报） 核心功能： - 支持日报模式（单个日期）和周期报模式（日期范围） - 自动读取指定日期的所有 Git 提交 - 对每个提交执行 git show 获取完整 diff - 使用 AI 分析 diff 内容提取实际工作内容 输出格式： - 只输出「工作内容」部分 - 每条以 - 开头，中文，简洁专业 - 格式：做了什么 + 改了哪里/达到什么效果 - 不输出：提交哈希、文件列表、统计数据、风险总结 使用示例： - 日报：git_work_report --date 2026-1-27 - 周期报：git_work_report --start_date 2026-2-1 --end_date 2026-2-6","write_action":false,"price_micros":0,"input_schema":null},{"name":"init_project","description":"当用户提供一句话需求时使用。基于 Spec-Driven Development 理念，分析需求并生成完整的项目规格文档（需求分析/技术设计/任务拆解）。适合项目初期的需求澄清和规划","write_action":false,"price_micros":0,"input_schema":null},{"name":"init_project_context","description":"生成/更新项目上下文写作计划（delegated）：MCP 写入 AGENTS.md 与 layout.json；project-context 分类文档与 graph-insights 由 Agent 按返回的 plan 落盘。新功能请先 start_feature，修 bug 请先 start_bugfix。","write_action":false,"price_micros":0,"input_schema":null},{"name":"interview","description":"当用户需求不明确、需要澄清需求时使用。需求访谈工具，在开发前通过结构化提问澄清需求，避免理解偏差和返工；生成访谈记录文件供后续 start_feature/add_feature 使用；仅支持 feature 类型","write_action":false,"price_micros":0,"input_schema":null},{"name":"list_memory_assets","description":"Memory Center 专用浏览动作。按更新时间列出记忆摘要，支持类型、状态、项目、标签和分页过滤；仅供 MCP App 调用。","write_action":false,"price_micros":0,"input_schema":null},{"name":"memorize_asset","description":"沉淀可检索记忆资产。支持成功经验及 failed_approach、false_root_cause、regression_case 负面记忆；负面记忆必须附 evidence，并建议填写 applicability。长流程应先准备 MemoryCandidate，并仅在 converge passed=true 后正式写入。","write_action":false,"price_micros":0,"input_schema":null},{"name":"plan_heartbeat","description":"由 Agent 在 Delegated Plan 执行过程中记录轻量检查点。首次调用必须提供完整 plan；后续合并步骤、证据、产物、候选经验、验收结果、运行证据和 revision。除 requirements 外，每条用于收敛的 evidence 必须至少提供 reference 或 revision，否则 converge 会明确拒绝。只记录状态，不代替 Agent 执行。","write_action":false,"price_micros":0,"input_schema":null},{"name":"read_memory_asset","description":"当编排阶段已检索到记忆摘要，且 AI 需要查看完整沉淀代码或详细规范时使用。根据 asset_id 读取记忆资产详情。","write_action":false,"price_micros":0,"input_schema":null},{"name":"refactor","description":"当用户需要重构代码、改善代码结构时使用。指南型工具：注入 code/file_path 与重构清单，由 Agent 分析后输出重构计划 JSON；MCP 不自动修改源文件","write_action":false,"price_micros":0,"input_schema":null},{"name":"resume_plan","description":"从 .mcp-probe-kit/plans/ 读取 Delegated Plan 检查点，按依赖计算下一可执行步骤、阻塞步骤和 resumeContext。plan_id 可选；省略时自动恢复当前项目最近更新的 active/blocked Plan。本工具只读取状态，不替 Agent 执行；返回 mustContinue=true 后 Agent 必须立即执行 nextStep/nextTool，逐步调用 plan_heartbeat，禁止只汇报恢复结果后停止。","write_action":false,"price_micros":0,"input_schema":null},{"name":"scan_and_extract_patterns","description":"当需要从单段代码、单文件或整个目录中抽取可复用模式，再决定是否沉淀到记忆系统时使用。目录扫描时，优先传 `project_root` 为项目根目录绝对路径，并让 `directory_path` 传相对项目根的路径，例如 `app/utils`；只有无法确定项目根时，才把 `directory_path` 直接设为绝对路径。不要传带项目名的半相对路径，例如 `font-miniapp-api/app/utils`。","write_action":false,"price_micros":0,"input_schema":null},{"name":"search_memory","description":"检索或浏览分层记忆库。默认 mode=semantic 按语义检索；Memory Center 可用 mode=browse 按更新时间分页浏览且不依赖 embedding。","write_action":false,"price_micros":0,"input_schema":null},{"name":"start_bugfix","description":"当用户需要找问题、修 bug、排查异常时使用。默认按 SRC-8（TBP-inspired）编排：收敛边界→真因工作表→修复→测试→记忆沉淀。","write_action":false,"price_micros":0,"input_schema":null},{"name":"start_feature","description":"新功能、功能增强、大版本升级或跨模块研发的首选入口。Agent 必须把当前对话已确认的完整目标、范围、模块、阶段和约束汇总到 description；用户只说“继续/开始/往下做”时不得原样透传。默认 spec_layout=auto，复杂多模块或多阶段需求会先生成 parent-child 子规格拆分计划，再进入 add_feature→check_spec→实现。仅在规格布局和子规格已明确、且只需渲染规格模板时才直接用 add_feature。","write_action":false,"price_micros":0,"input_schema":null},{"name":"start_onboard","description":"当用户需要快速上手新项目时使用。编排：生成上下文文档。","write_action":false,"price_micros":0,"input_schema":null},{"name":"start_product","description":"产品设计完整工作流入口。返回闭环 delegated plan：Agent 生成 PRD 与原型文档，调用 ui_design_system 和 start_ui 完成设计系统及可交互 HTML 原型，并更新项目上下文；不会引用不存在的 gen_prd/gen_prototype 工具。","write_action":false,"price_micros":0,"input_schema":null},{"name":"start_ralph","description":"用于需要多轮小步实现、每轮真实验证和正式收敛的长任务。返回有界 Delegated Plan、每轮 Heartbeat 证据契约和可选前台辅助脚本；不自动运行循环、不创建后台进程。安全停止不等于成功","write_action":false,"price_micros":0,"input_schema":null},{"name":"start_ui","description":"编排 UI 设计与实现：先锁定视觉方向和信息架构，再生成关键页面，后续通过真实截图评分与迭代完成验收。","write_action":false,"price_micros":0,"input_schema":null},{"name":"sync_ui_data","description":"同步 UI/UX 数据到本地缓存。来源：uipro-cli、shadcn/ui registry、内嵌 UI 主题预设、Vercel Web Interface Guidelines。","write_action":false,"price_micros":0,"input_schema":null},{"name":"ui_design_system","description":"生成可执行的视觉方向，而不是风格标签拼盘。输出核心任务、信息架构、内容密度、排版与色彩策略、组件原则、明确禁用项和截图验收标准。","write_action":false,"price_micros":0,"input_schema":null},{"name":"ui_search","description":"搜索页面结构、组件、交互规范和实现参考。新 UI 流程优先使用 structure 模式按任务和页面类型选择信息架构；旧 search/catalog/template 模式继续兼容。","write_action":false,"price_micros":0,"input_schema":null},{"name":"update_memory_asset","description":"按 asset_id 更新已有记忆资产（保留原 ID）。可修正内容、证据、适用边界、失效时间及替代关系；content 或生命周期语义变化会重新向量化。","write_action":true,"price_micros":0,"input_schema":null},{"name":"workflow","description":"仅当 Agent 阅读 Skill 和各工具 description 后仍不确定该调用哪个 MCP 时使用的兜底选择指南。workflow 不做自然语言意图识别：scenario=auto（默认）只返回工具选择规则与速查表，不从 intent 猜 firstTool；Agent 根据完整对话自行判断或澄清。若 Agent 已明确场景，可传显式 scenario 获取该场景的确定性 firstTool、phases 和参数提示。同时确保用户项目已存在 .agents/skills/mcp-probe-kit/SKILL.md 与 AGENTS.md 中的 Skill 引用（缺失则自动创建/更新）。","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":92,"grade":"A","scanned_at":"2026-11-04T06:35:22.086Z","report":{"scannerVersion":"0.1.10","scannedAt":"2026-11-04T06:35:22.023Z","components":{"code":{"score":25,"max":25,"notes":["445 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":15,"max":15,"notes":["last push 0 days ago"]},"identity":{"score":8,"max":10,"notes":["registry namespace matches repository owner","GitHub account older than a year"]}},"findings":[],"inputs":{"packages":[{"registryType":"npm","identifier":"mcp-probe-kit","version":"4.0.0","found":true,"license":"MIT","hasInstallScripts":false,"dependencyCount":7,"publishedAt":"2026-08-11T08:08:21.720Z","repositoryUrl":"git+https://github.com/mybolide/mcp-probe-kit.git","weeklyDownloads":156}],"repo":{"found":true,"owner":"mybolide","repo":"mcp-probe-kit","archived":false,"pushedAt":"2026-11-04T05:50:48Z","stars":41,"forks":5,"openIssues":0,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/13502882?v=4","ownerCreatedAt":"2015-07-26T01:50:41Z","license":"MIT"},"icon":{"url":"https://avatars.githubusercontent.com/u/13502882?v=4&s=128","source":"registry","width":128,"height":128},"presence":{"stars":41,"forks":5,"downloadsWeek":156,"license":"MIT","lastPushAt":"2026-11-04T05:50:48.000Z","score":42}}}},"grade_history":[],"reviews":[]}