{"id":32675615,"url":"https://github.com/mybolide/mcp-probe-kit","last_synced_at":"2026-03-15T19:45:56.811Z","repository":{"id":320717508,"uuid":"1082969952","full_name":"mybolide/mcp-probe-kit","owner":"mybolide","description":"mcp-probe-kit is a protocol-level toolkit designed for developers who want AI to truly understand their project's intent. It's not just a collection of 22 tools—it's a context-aware system that helps AI agents grasp what you're building.","archived":false,"fork":false,"pushed_at":"2026-03-13T10:32:02.000Z","size":20664,"stargazers_count":34,"open_issues_count":0,"forks_count":4,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-13T22:51:31.130Z","etag":null,"topics":["ai","ai-tools","cursor","development-tools","mcp","skills"],"latest_commit_sha":null,"homepage":"https://mcp-probe-kit.bytezonex.com/","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mybolide.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":null},"created_at":"2025-10-25T04:48:05.000Z","updated_at":"2026-03-13T10:31:48.000Z","dependencies_parsed_at":"2025-10-25T13:23:09.900Z","dependency_job_id":"da37b0d9-762e-4a85-878b-3307b25191c5","html_url":"https://github.com/mybolide/mcp-probe-kit","commit_stats":null,"previous_names":["mybolide/mcp-probe-kit"],"tags_count":42,"template":false,"template_full_name":null,"purl":"pkg:github/mybolide/mcp-probe-kit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mybolide%2Fmcp-probe-kit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mybolide%2Fmcp-probe-kit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mybolide%2Fmcp-probe-kit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mybolide%2Fmcp-probe-kit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mybolide","download_url":"https://codeload.github.com/mybolide/mcp-probe-kit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mybolide%2Fmcp-probe-kit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30550742,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-15T15:03:43.933Z","status":"ssl_error","status_checked_at":"2026-03-15T15:03:37.630Z","response_time":61,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","ai-tools","cursor","development-tools","mcp","skills"],"created_at":"2025-11-01T06:02:03.893Z","updated_at":"2026-03-15T19:45:56.797Z","avatar_url":"https://github.com/mybolide.png","language":"TypeScript","funding_links":[],"categories":["MCP 服务器精选列表"],"sub_categories":["💻 开发与代码执行"],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"docs/assets/logo.png\" alt=\"知时MCP Logo\" width=\"160\"/\u003e\n  \u003ch1\u003e知时MCP | mcp-probe-kit\u003c/h1\u003e\n  \u003cp\u003e\u003cstrong\u003eKnow the Context, Feed the Moment.\u003c/strong\u003e\u003c/p\u003e\n  \u003cp\u003e\n    \u003ccode\u003eIntrospection\u003c/code\u003e · \u003ccode\u003eContext Hydration\u003c/code\u003e · \u003ccode\u003eDelegated Orchestration\u003c/code\u003e\n  \u003c/p\u003e\n\u003c/div\u003e\n\n---\n\n\u003c!-- mcp-name: io.github.mybolide/mcp-probe-kit --\u003e\n\n\u003e **Talk is cheap, show me the Context.**\n\u003e \n\u003e mcp-probe-kit is a protocol-level toolkit designed for developers who want AI to truly understand their project's intent. It's not just a collection of 22 tools—it's a context-aware system that helps AI agents grasp what you're building.\n\n**Languages**: [English](README.md) | [简体中文](i18n/README.zh-CN.md) | [日本語](i18n/README.ja-JP.md) | [한국어](i18n/README.ko-KR.md) | [Español](i18n/README.es-ES.md) | [Français](i18n/README.fr-FR.md) | [Deutsch](i18n/README.de-DE.md) | [Português (BR)](i18n/README.pt-BR.md)\n\n[![npm version](https://img.shields.io/npm/v/mcp-probe-kit.svg)](https://www.npmjs.com/package/mcp-probe-kit)\n[![npm downloads](https://img.shields.io/npm/dm/mcp-probe-kit.svg)](https://www.npmjs.com/package/mcp-probe-kit)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![GitHub stars](https://img.shields.io/github/stars/mybolide/mcp-probe-kit.svg)](https://github.com/mybolide/mcp-probe-kit/stargazers)\n\n\u003e 🚀 AI-Powered Complete Development Toolkit - Covering the Entire Development Lifecycle\n\nA powerful MCP (Model Context Protocol) server providing **22 tools** covering the complete workflow from product analysis to final release (Requirements → Design → Development → Quality → Release), all tools support **structured output**.\n\n**🎉 v3.0 Major Update**: Streamlined tool count, focus on core competencies, eliminate choice paralysis, let AI do more native work\n\n**Supports All MCP Clients**: Cursor, Claude Desktop, Cline, Continue, and more\n\n**Protocol Version**: MCP 2025-11-25 · **SDK**: @modelcontextprotocol/sdk 1.27.1\n\n---\n\n## 📚 Complete Documentation\n\n**👉 [https://mcp-probe-kit.bytezonex.com](https://mcp-probe-kit.bytezonex.com/)**\n\n- [Quick Start](https://mcp-probe-kit.bytezonex.com/pages/getting-started.html) - Setup in 5 minutes\n- [All Tools](https://mcp-probe-kit.bytezonex.com/pages/all-tools.html) - Complete list of 22 tools\n- [Best Practices](https://mcp-probe-kit.bytezonex.com/pages/examples.html) - Full development workflow guide\n- [v3.0 Migration Guide](https://mcp-probe-kit.bytezonex.com/pages/migration.html) - Upgrade from v2.x to v3.0\n\n---\n\n## ✨ Core Features\n\n### 📦 22 Tools\n\n- **🔄 Workflow Orchestration** (6 tools) - One-click complex development workflows\n  - `start_feature`, `start_bugfix`, `start_onboard`, `start_ui`, `start_product`, `start_ralph`\n- **🔍 Code Analysis** (4 tools) - Code quality, refactoring, and graph insight\n  - `code_review`, `code_insight`, `fix_bug`, `refactor`\n- **📝 Git Tools** (2 tools) - Git commits and work reports\n  - `gencommit`, `git_work_report`\n- **⚡ Code Generation** (1 tool) - Test generation\n  - `gentest`\n- **📦 Project Management** (6 tools) - Project initialization and requirements management\n  - `init_project`, `init_project_context`, `add_feature`, `estimate`, `interview`, `ask_user`\n- **🎨 UI/UX Tools** (3 tools) - Design systems and data synchronization\n  - `ui_design_system`, `ui_search`, `sync_ui_data`\n\n### 🧠 Code Graph Bridge (GitNexus)\n\n- `code_insight` bridges GitNexus by default for query/context/impact analysis\n- The bridge launches `npx -y gitnexus@latest mcp` by default to reduce stale package risk\n- `init_project_context` bootstraps baseline graph docs under `docs/graph-insights/`; if `docs/project-context.md` already exists, it preserves the old context docs and only backfills graph docs plus the index entry\n- `start_feature` refreshes the GitNexus index and runs task-level `query/context/impact` narrowing before spec generation to reduce over-scoping\n- `start_bugfix` refreshes the GitNexus index and runs task-level graph analysis before TBP RCA to constrain failure boundary and blast radius\n- Older projects that already have `project-context.md` but no graph docs are bootstrapped automatically through the `init_project_context` step\n- If GitNexus is unavailable, the server falls back automatically without breaking orchestration\n- Real graph queries read the `.gitnexus` index; `docs/graph-insights/latest.md|json` are readable snapshots for humans and AI agents\n- Graph snapshots are exposed as resources (`probe://graph/latest`, `probe://graph/history`, `probe://graph/latest.md`)\n- Graph snapshots are also persisted to readable files in `.mcp-probe-kit/graph-snapshots` (customizable via `MCP_GRAPH_SNAPSHOT_DIR`)\n- Tool responses include `_meta.graph` with snapshot URI and local JSON/Markdown file paths\n\n### 🐛 TBP 8-Step RCA for Bug Workflows\n\n- `start_bugfix` defaults to Toyota-style TBP 8-step root-cause analysis before repair\n- `fix_bug` returns a structured TBP skeleton covering phenomenon, timeline, ruled-out paths, boundary, root cause, evidence, and repair plan\n- This makes bug, regression, anomaly, and \"why didn't it work\" investigations follow analyze-first discipline instead of patching symptoms\n\n### 🎯 Structured Output\n\nCore and orchestration tools support **structured output**, returning machine-readable JSON data, improving AI parsing accuracy, supporting tool chaining and state tracking.\n\n### ⏱️ Native Tasks, Progress, and Cancellation\n\n- Built on MCP SDK native task support (`taskStore` + `taskMessageQueue`)\n- Supports task lifecycle endpoints: `tasks/get`, `tasks/result`, `tasks/list`, `tasks/cancel`\n- Advertises `capabilities.tasks.requests.tools.call` so clients can create tasks for `tools/call`\n- Emits `notifications/progress` when client provides `_meta.progressToken`\n- Handles request cancellation via `AbortSignal` and returns a clear cancellation error\n- Long-running orchestration tools (`start_*`) and `sync_ui_data` support cooperative cancellation/progress callbacks\n\n### 🔌 Extensions \u0026 UI Apps (Optional)\n\n- Trace metadata passthrough: request `_meta.trace` is preserved in tool responses (`_meta.trace`)\n- Optional extensions capability switch: enable with `MCP_ENABLE_EXTENSIONS_CAPABILITY=1`\n- Optional MCP Apps resource output for UI tools: enable with `MCP_ENABLE_UI_APPS=1`\n- UI tools can expose preview resources via `ui://...` and response `_meta.ui.resourceUri`\n\n### 🧭 Delegated Orchestration Protocol\n\nAll `start_*` orchestration tools return an **execution plan** in `structuredContent.metadata.plan`.  \nAI needs to **call tools step by step and persist files**, rather than the tool executing internally.\n\n**Plan Schema (Core Fields)**:\n```json\n{\n  \"mode\": \"delegated\",\n  \"steps\": [\n    {\n      \"id\": \"spec\",\n      \"tool\": \"add_feature\",\n      \"args\": { \"feature_name\": \"user-auth\", \"description\": \"User authentication feature\" },\n      \"outputs\": [\"docs/specs/user-auth/requirements.md\"]\n    }\n  ]\n}\n```\n\n**Field Description**:\n- `mode`: Fixed as `delegated`\n- `steps`: Array of execution steps\n- `tool`: Tool name (e.g. `add_feature`)\n- `action`: Manual action description when no tool (e.g. `update_project_context`)\n- `args`: Tool parameters\n- `outputs`: Expected artifacts\n- `when/dependsOn/note`: Optional conditions and notes\n\n### 🧩 Structured Output Field Specification (Key Fields)\n\nBoth orchestration and atomic tools return `structuredContent`, common fields:\n- `summary`: One-line summary\n- `status`: Status (pending/success/failed/partial)\n- `steps`: Execution steps (orchestration tools)\n- `artifacts`: Artifact list (path + purpose)\n- `metadata.plan`: Delegated execution plan (only start_*)\n- `specArtifacts`: Specification artifacts (start_feature)\n- `estimate`: Estimation results (start_feature / estimate)\n\n### 🧠 Requirements Clarification Mode (Requirements Loop)\n\nWhen requirements are unclear, use `requirements_mode=loop` in `start_feature / start_bugfix / start_ui`.  \nThis mode performs 1-2 rounds of structured clarification before entering spec/fix/UI execution.\n\n**Example:**\n```json\n{\n  \"feature_name\": \"user-auth\",\n  \"description\": \"User authentication feature\",\n  \"requirements_mode\": \"loop\",\n  \"loop_max_rounds\": 2,\n  \"loop_question_budget\": 5\n}\n```\n\n### 🧩 Template System (Regular Model Friendly)\n\n`add_feature` supports template profiles, default `auto` auto-selects: prefers `guided` when requirements are incomplete (includes detailed filling rules and checklists), selects `strict` when requirements are complete (more compact structure, suitable for high-capability models or archival scenarios).\n\n**Example:**\n```json\n{\n  \"description\": \"Add user authentication feature\",\n  \"template_profile\": \"auto\"\n}\n```\n\n**Applicable Tools**:\n- `start_feature` passes `template_profile` to `add_feature`\n- `start_bugfix` / `start_ui` also support `template_profile` for controlling guidance strength (auto/guided/strict)\n\n**Template Profile Strategy**:\n- `guided`: Less/incomplete requirements info, regular model priority\n- `strict`: Requirements structured, prefer more compact guidance\n- `auto`: Default recommendation, auto-selects guided/strict\n\n### 🔄 Workflow Orchestration\n\n6 intelligent orchestration tools that automatically combine multiple basic tools for one-click complex development workflows:\n- `start_feature` - New feature development (Requirements → Design → Estimation)\n- `start_bugfix` - Bug fixing (TBP 8-step RCA → Fix → Testing)\n- `start_onboard` - Project onboarding (Generate project context docs)\n- `start_ui` - UI development (Design system → Components → Code)\n- `start_product` - Product design (PRD → Prototype → Design system → HTML)\n- `start_ralph` - Ralph Loop (Iterative development until goal completion)\n\n### 🚀 Product Design Workflow\n\n`start_product` is a complete product design orchestration tool, from requirements to interactive prototype:\n\n**Workflow:**\n1. **Requirements Analysis** - Generate standard PRD (product overview, feature requirements, page list)\n2. **Prototype Design** - Generate detailed prototype docs for each page\n3. **Design System** - Generate design specifications based on product type\n4. **HTML Prototype** - Generate interactive prototype viewable in browser\n5. **Project Context** - Auto-update project documentation\n\n**Structured Output Additions**:\n- `start_product.structuredContent.artifacts`: Artifact list (PRD, prototypes, design system, etc.)\n- `interview.structuredContent.mode`: `usage` / `questions` / `record`\n\n### 🎨 UI/UX Pro Max\n\n3 UI/UX tools with `start_ui` as the unified entry point:\n- `start_ui` - One-click UI development (supports intelligent mode) (orchestration tool)\n- `ui_design_system` - Intelligent design system generation\n- `ui_search` - UI/UX data search (BM25 algorithm)\n- `sync_ui_data` - Sync latest UI/UX data locally\n\n**Note**: `start_ui` automatically calls `ui_design_system` and `ui_search`, you don't need to call them separately.\n\n**Inspiration:**\n- [ui-ux-pro-max-skill](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill) - UI/UX design system philosophy\n- [json-render](https://github.com/vercel-labs/json-render) - JSON template rendering engine\n\n**Why use `sync_ui_data`?**\n\nOur `start_ui` tool relies on a rich UI/UX database (colors, icons, charts, components, design patterns, etc.) to generate high-quality design systems and code. This data comes from npm package [uipro-cli](https://www.npmjs.com/package/uipro-cli), including:\n- 🎨 Color schemes (mainstream brand colors, color palettes)\n- 🔣 Icon libraries (React Icons, Heroicons, etc.)\n- 📊 Chart components (Recharts, Chart.js, etc.)\n- 🎯 Landing page templates (SaaS, e-commerce, government, etc.)\n- 📐 Design specifications (spacing, fonts, shadows, etc.)\n\n**Data Sync Strategy:**\n1. **Embedded Data**: Synced at build time, works offline\n2. **Cached Data**: Runtime updates to `~/.mcp-probe-kit/ui-ux-data/`\n3. **Manual Sync**: Use `sync_ui_data` to force update latest data\n\nThis ensures `start_ui` can generate professional-grade UI code even offline.\n\n### 🎤 Requirements Interview\n\n2 interview tools to clarify requirements before development:\n- `interview` - Structured requirements interview\n- `ask_user` - AI proactive questioning\n\n---\n\n## 🧭 Tool Selection Guide\n\n### When to use orchestration tools vs individual tools?\n\n**Use orchestration tools (start_*) when:**\n- ✅ Need complete workflow (multiple steps)\n- ✅ Want to automate multiple tasks\n- ✅ Need to generate multiple artifacts (docs, code, tests, etc.)\n\n**Use individual tools when:**\n- ✅ Only need specific functionality\n- ✅ Already have project context docs\n- ✅ Need more fine-grained control\n\n### Common Scenario Selection\n\n| Scenario | Recommended Tool | Reason |\n|---------|-----------------|--------|\n| Develop new feature (complete flow) | `start_feature` | Auto-complete: spec→estimation |\n| Only need feature spec docs | `add_feature` | More lightweight, only generates docs |\n| Fix bug (complete flow) | `start_bugfix` | Root-cause-first flow: TBP RCA → fix → test |\n| Only need bug analysis | `fix_bug` | TBP 8-step RCA only, without full orchestration |\n| Generate design system | `ui_design_system` | Directly generate design specs |\n| Develop UI components | `start_ui` | Complete flow: design→components→code |\n| Product design (requirements to prototype) | `start_product` | One-click: PRD→prototype→HTML |\n| One-sentence requirement analysis | `init_project` | Generate complete project spec docs |\n| Project onboarding docs | `init_project_context` | Generate tech stack/architecture/conventions |\n\n---\n\n## 🚀 Quick Start\n\n### Method 1: Use directly with npx (Recommended)\n\nNo installation needed, use the latest version directly.\n\n#### Cursor / Cline Configuration\n\n**Config file location:**\n- Windows: `%APPDATA%\\Cursor\\User\\globalStorage\\saoudrizwan.claude-dev\\settings\\cline_mcp_settings.json`\n- macOS: `~/Library/Application Support/Cursor/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json`\n- Linux: `~/.config/Cursor/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json`\n\n**Config content:**\n```json\n{\n  \"mcpServers\": {\n    \"mcp-probe-kit\": {\n      \"command\": \"npx\",\n      \"args\": [\"mcp-probe-kit@latest\"]\n    }\n  }\n}\n```\n\n#### Claude Desktop Configuration\n\n**Config file location:**\n- Windows: `%APPDATA%\\Claude\\claude_desktop_config.json`\n- macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`\n- Linux: `~/.config/Claude/claude_desktop_config.json`\n\n**Config content:**\n```json\n{\n  \"mcpServers\": {\n    \"mcp-probe-kit\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-probe-kit@latest\"]\n    }\n  }\n}\n```\n\n### Method 2: Global Installation\n\n```bash\nnpm install -g mcp-probe-kit\n```\n\nUse in config file:\n```json\n{\n  \"mcpServers\": {\n    \"mcp-probe-kit\": {\n      \"command\": \"mcp-probe-kit\"\n    }\n  }\n}\n```\n\n### Windows Notes for Graph Tools\n\nApplies to `code_insight`, `start_feature`, `start_bugfix`, and `init_project_context`.\n\n- The GitNexus bridge uses `npx -y gitnexus@latest mcp` by default.\n- On Windows, the first cold start can take 20+ seconds because `npx` may check/download packages.\n- Some GitNexus dependencies use `tree-sitter-*` native modules. If your machine lacks Visual Studio Build Tools, the first install may fail with errors like `gyp ERR! find VS could not find a version of Visual Studio 2017 or newer to use`.\n\nRecommended on Windows:\n\n1. Install Visual Studio Build Tools with the C++ workload if you use graph-aware tools regularly.\n2. Prefer stable local/global CLI usage for GitNexus when your MCP client supports `env`.\n3. Increase GitNexus connect/call timeouts on slower or first-run environments.\n\nQuick install command (Windows):\n\n```powershell\nwinget install Microsoft.VisualStudio.2022.BuildTools\n```\n\nExample config using a preinstalled `gitnexus` CLI:\n\n```json\n{\n  \"mcpServers\": {\n    \"mcp-probe-kit\": {\n      \"command\": \"mcp-probe-kit\",\n      \"env\": {\n        \"MCP_GITNEXUS_COMMAND\": \"gitnexus\",\n        \"MCP_GITNEXUS_ARGS\": \"mcp\",\n        \"MCP_GITNEXUS_CONNECT_TIMEOUT_MS\": \"30000\",\n        \"MCP_GITNEXUS_TIMEOUT_MS\": \"45000\"\n      }\n    }\n  }\n}\n```\n\n### Restart Client\n\nAfter configuration, **completely quit and reopen** your MCP client.\n\n**👉 [Detailed Installation Guide](https://mcp-probe-kit.bytezonex.com/pages/getting-started.html)**\n\n---\n\n## 💡 Usage Examples\n\n### Daily Development\n```bash\ncode_review @feature.ts    # Code review\ngentest @feature.ts         # Generate tests\ngencommit                   # Generate commit message\n```\n\n### New Feature Development\n```bash\nstart_feature user-auth \"User authentication feature\"\n# Auto-complete: Requirements analysis → Design → Effort estimation\n```\n\n### Bug Fixing\n```bash\nstart_bugfix\n# Then paste error message\n# Auto-complete: Problem location → Fix solution → Test code\n```\n\n### Product Design\n```bash\nstart_product \"Online Education Platform\" --product_type=SaaS\n# Auto-complete: PRD → Prototype → Design system → HTML prototype\n```\n\n### UI Development\n```bash\nstart_ui \"Login Page\" --mode=auto\n# Auto-complete: Design system → Component generation → Code output\n```\n\n### Project Context Documentation\n```bash\n# Single file mode (default) - Generate a complete project-context.md\ninit_project_context\n\n# Modular mode - Generate 6 category docs (suitable for large projects)\ninit_project_context --mode=modular\n# Generates: project-context.md (index) + 5 category docs\n```\n\n### Git Work Report\n```bash\n# Generate daily report\ngit_work_report --date 2026-02-03\n\n# Generate weekly report\ngit_work_report --start_date 2026-02-01 --end_date 2026-02-07\n\n# Save to file\ngit_work_report --date 2026-02-03 --output_file daily-report.md\n# Auto-analyze Git diff, generate concise professional report\n# If direct command fails, auto-provides temp script solution (auto-deletes after execution)\n```\n\n**👉 [More Usage Examples](https://mcp-probe-kit.bytezonex.com/pages/examples.html)**\n\n---\n\n## ❓ FAQ\n\n### Q1: Tool not working or errors?\n\nCheck detailed logs:\n\n**Windows (PowerShell):**\n```powershell\nnpx -y mcp-probe-kit@latest 2\u003e\u00261 | Tee-Object -FilePath .\\mcp-probe-kit.log\n```\n\n**macOS/Linux:**\n```bash\nnpx -y mcp-probe-kit@latest 2\u003e\u00261 | tee ./mcp-probe-kit.log\n```\n\n### Q2: Client not recognizing tools after configuration?\n\n1. **Restart client** (completely quit then reopen)\n2. Check config file path is correct\n3. Confirm JSON format is correct, no syntax errors\n4. Check client developer tools or logs for error messages\n\n### Q3: How to update to latest version?\n\n**npx method (Recommended):**\nUse `@latest` tag in config, automatically uses latest version.\n\n**Global installation method:**\n```bash\nnpm update -g mcp-probe-kit\n```\n\n### Q4: Why are graph-aware tools slow or timing out on Windows the first time?\n\nThis usually affects `code_insight`, `start_feature`, `start_bugfix`, and `init_project_context`.\n\nCommon causes:\n\n1. `npx -y gitnexus@latest mcp` performs a cold start and may spend 20+ seconds checking/downloading packages.\n2. GitNexus may need native `tree-sitter-*` modules, which can require Visual Studio Build Tools on Windows.\n\nIf you see logs like:\n\n```text\ngyp ERR! find VS could not find a version of Visual Studio 2017 or newer to use\ngyp ERR! find VS - missing any VC++ toolset\n```\n\nTry this:\n\n1. Install Visual Studio Build Tools with the C++ workload.\n2. Retry once after dependencies finish installing.\n3. If your client supports `env`, switch the bridge to a preinstalled `gitnexus` CLI and raise:\n   `MCP_GITNEXUS_CONNECT_TIMEOUT_MS`\n   `MCP_GITNEXUS_TIMEOUT_MS`\n\n**👉 [More FAQ](https://mcp-probe-kit.bytezonex.com/pages/getting-started.html)**\n\n---\n\n## 🤝 Contributing\n\nIssues and Pull Requests welcome!\n\n**Improvement suggestions:**\n- Add useful tools\n- Optimize existing tool prompts\n- Improve documentation and examples\n- Fix bugs\n\n---\n\n## 📄 License\n\nMIT License\n\n---\n\n## 🔗 Related Links\n\n- **Author**: [Kyle (小墨)](https://www.bytezonex.com/)\n- **GitHub**: [mcp-probe-kit](https://github.com/mybolide/mcp-probe-kit)\n- **npm**: [mcp-probe-kit](https://www.npmjs.com/package/mcp-probe-kit)\n- **Documentation**: [https://mcp-probe-kit.bytezonex.com](https://mcp-probe-kit.bytezonex.com/)\n\n**Related Projects:**\n- [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) - Official MCP protocol docs\n- [GitHub Spec-Kit](https://github.com/github/spec-kit) - GitHub spec-driven development toolkit\n- [ui-ux-pro-max-skill](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill) - UI/UX design system philosophy source\n- [json-render](https://github.com/vercel-labs/json-render) - JSON template rendering engine inspiration\n- [uipro-cli](https://www.npmjs.com/package/uipro-cli) - UI/UX data source\n\n---\n\n**Made with ❤️ for AI-Powered Development**\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmybolide%2Fmcp-probe-kit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmybolide%2Fmcp-probe-kit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmybolide%2Fmcp-probe-kit/lists"}