Kaiord

Name: Kaiord
Author: pablo-albaladejo

作者：pablo-albaladejo版本 10.5.0i★ –i电脑或云端

注册名称io.github.pablo-albaladejo/kaiord

安装

概览

作者提供的说明（英文原文）

Convert, validate, and inspect workout files (FIT, TCX, ZWO, Garmin Connect) for AI agents.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i3 项中通过 3 项依据公开信息检查；尚未扫描代码
使用情况i非常新↓ 159/周 · ★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 电脑或云端
传输方式: stdio, Streamable HTTP
分类: 诊所与健康

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：3 项中通过 3 项
在作者的服务器上运行：你向它提出的内容会经过他们的服务器。
可以做 8 件事（工具） kaiord_get_format_spec, kaiord_list_formats, kaiord_convert, kaiord_validate …
注册中心没有列出需要填写的密钥。

你需要

在云端运行无需安装任何东西，通过互联网连接
npm已安装 Node.js（用于 npx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude：

打开 Settings → Connectors
点击 Add custom connector
粘贴下面的地址，然后点击 Add
如果要求登录，请登录作者的服务

https://kaiord.com/mcp

或者在你的电脑上运行

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "kaiord": {
      "command": "npx",
      "args": [
        "-y",
        "@kaiord/mcp"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add --transport http kaiord https://kaiord.com/mcp

或者在你的电脑上运行

claude mcp add kaiord -- npx -y @kaiord/mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "kaiord": {
      "url": "https://kaiord.com/mcp"
    }
  }
}

或者在你的电脑上运行

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "kaiord": {
      "command": "npx",
      "args": [
        "-y",
        "@kaiord/mcp"
      ]
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "kaiord": {
      "type": "http",
      "url": "https://kaiord.com/mcp"
    }
  }
}

或者在你的电脑上运行

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "kaiord": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@kaiord/mcp"
      ]
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

ChatGPT 只能连接互联网上的服务器：

打开网页版 ChatGPT → Settings → Connectors (Apps)
点击 Create 或 Add（部分套餐需要先在 Advanced 中开启 Developer mode）
粘贴下面的地址，起个名字，然后保存
如果要求登录，请登录作者的服务

https://kaiord.com/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上，无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

工具名称和描述与服务器在 2026年11月7日报告的完全一致。这些内容由作者撰写，不是我们写的；我们以纯文本形式显示。

kaiord_get_format_spec
Get the KRD format specification. Call this before creating or editing KRD documents.
kaiord_list_formats
List all supported fitness data formats with capabilities
kaiord_convert
Convert between fitness data formats (FIT, TCX, ZWO, GCN, KRD). FIT output is returned as base64 text unless output_file is given. On the remote endpoint, ZWO input is checked for well-formedness only, not against the XSD, and only structured workouts are accepted.
kaiord_validate
Validate a KRD JSON document against the schema On the remote endpoint, ZWO input is checked for well-formedness only, not against the XSD, and only structured workouts are accepted.
kaiord_round_trip_validate
Validate round-trip FIT conversion (FIT → KRD → FIT) and report tolerance violations
kaiord_inspect
Inspect a fitness file and return a human-readable summary
kaiord_extract_workout
Extract the structured workout from a fitness file as JSON
kaiord_diff
Compare two fitness files and show differences

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月10日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 pablo-albaladejo 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
✓ 通过
端点有响应
在 358 毫秒内响应（HTTP 200）
– 不适用
使用 OAuth 登录
无需登录
✓ 通过
工具描述中没有隐藏指令
已读取 8 个工具描述，未发现针对 AI 的隐藏指令

与“诊所与健康”中的其他服务器比较i

星标数多于此分类中其他 1061 个服务器的 0%
发布到注册中心的时间比此分类中其他 1061 个服务器的 69% 更新
基础检查结果等于或优于此分类中其他 1061 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Kaiord 安全吗？

它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

两种方式都可以：安装在你的电脑上，或者连接云端版本。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（10.5.0）于11天前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接，所以接受远程 MCP 服务器的应用也可以使用，例如开启开发者模式的 ChatGPT。

有什么可以替代它？

同一分类中有：Mirobody, FHIR MCP Server, Google Health MCP

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：↓ 每周下载量i★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Mirobody

Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.

作者：thetahealth正在增长↓ 290/周★ 14083天前更新

在你的电脑上运行✓ thetahealth.ai

安装

FHIR MCP Server

MCP server providing seamless access to FHIR APIs for AI tools and healthcare applications

作者：wso2正在增长↓ 823/周★ 13712天前更新

在你的电脑上运行

安装

Google Health MCP

Privacy-first unofficial Google Health API v4 MCP server for health, sleep, activity, HR agents

作者：davidmosiah正在增长↓ 1024/周★ 794个月前更新

在你的电脑上运行

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Kaiord — Open-Source Health & Fitness Data Framework

[kaiord.com](https://kaiord.com) | Editor | npm

Kaiord is an open-source framework for creating, converting, and managing health & fitness data.

It provides:

@kaiord/core: a TypeScript library with format adapters for .fit, .tcx, .zwo, and .krd (Kaiord) files, plus Garmin Connect API integration.
@kaiord/cli: a command-line tool to convert, validate, and compare files across formats.
@kaiord/mcp: an MCP server exposing Kaiord tools to AI agents (Claude Desktop, Claude Code, etc.). Published in the official MCP registry as io.github.pablo-albaladejo/kaiord.
[Workout Editor](https://kaiord.com/app/): a web application to create and edit workout files visually.

✨ Features

[Visual Workout Editor](https://kaiord.com/app/) - Create and edit workouts in your browser
Unified JSON-based format .krd (Kaiord Representation Definition)
Schema validation (Zod)
Round-trip safe conversions between FIT / TCX / ZWO / GCN / KRD
Hexagonal architecture & fully typed API

Supported FIT Fields

Workout Metadata

Sub-sport categorization: Detailed sport types (trail running, indoor cycling, lap swimming, etc.)
Pool dimensions: Pool length and unit for swimming workouts

Workout Steps

Coaching notes: Instructional text for each step (max 256 characters)
Swimming equipment: Fins, kickboard, paddles, pull buoy, snorkel

Duration Types

Time & distance: Standard interval durations
Calorie-based: Steps ending after burning specified calories
Power-based: Steps ending based on power thresholds (watts)
Heart rate conditionals: Steps ending based on HR thresholds (bpm)
Repeat conditionals: Repeat blocks until time/distance/calories/HR/power targets reached

Known Limitations

Training Stress Score (TSS): The training_peaks_tss duration type is not yet implemented in the FIT converter. This is a TrainingPeaks-specific metric that requires additional mapping logic. Contributions welcome!

🔒 Local-first architecture

Kaiord is local-first: your data lives on your device, because there is no Kaiord server to send it to. There are no accounts and no backend.

Storage is your browser's IndexedDB. The Workout Editor persists every workout, template, profile, and setting in a local Dexie.js / IndexedDB database (new KaiordDatabase() in dexie-database.ts), and the UI reads it reactively through useLiveQuery. Nothing is written to a remote database — see the "Persisted data → Dexie" rule in State Management.
Conversions run entirely on your machine. FIT / TCX / ZWO / GCN ↔ KRD conversion happens in-process — client-side in the editor (import-workout-formats.ts, export-workout-formats.ts) or locally in the @kaiord/cli. Files never leave your device to be converted.
Sync is opt-in and goes to _your_ cloud. Data leaves the device only if you connect Google Drive. The cloud-sync adapter uses the Google Identity Services drive.appdata scope, so synced data lands in your own Drive's app folder; the access token lives only in memory for the session and is never persisted by Kaiord.
Integrations use _your_ logged-in session — no credential proxy. Garmin, WHOOP, and Train2Go connect through browser-extension "bridges" (garmin-bridge, whoop-bridge, train2go-bridge) that piggyback on your existing browser session. Per openspec/specs/adapter-contracts/spec.md, a bridge "SHALL NOT store, transmit, or manage user credentials"; authentication is "delegated entirely to the browser's cookie jar." No third-party server proxies your credentials or your data.
Works offline. Because all logic and storage are client-side, the editor keeps working with no network connection once loaded.

📚 Documentation

Comprehensive documentation is available in the /docs directory:

[Getting Started](./docs/getting-started.md) - Installation, basic usage, and quick examples for both library and CLI
[Architecture](./docs/architecture.md) - Hexagonal architecture, ports & adapters pattern, and design principles
[Testing](./docs/testing.md) - Testing strategy, TDD workflow, and coverage requirements
[Deployment](./docs/deployment.md) - CI/CD pipeline, GitHub Pages deployment, and npm publishing
[Contributing](./CONTRIBUTING.md) - Contribution guidelines, development workflow, and code standards
[KRD Format](./docs/krd-format.md) - Complete specification of the Kaiord Representation Definition format
[AI Agents](./AGENTS.md) - Guidance for AI-assisted development

🧩 Tech Stack

Layer	Tooling
Core	TypeScript, tsdown, Zod
CLI	yargs
Web App	React, Zustand, Tailwind, Radix UI
Testing	Vitest, Playwright
Package manager	pnpm

🏗 Monorepo Layout

kaiord/

├─ packages/ │ ├─ core/ → domain types, schemas, ports & use cases │ ├─ fit/ → Garmin FIT format adapter │ ├─ tcx/ → Training Center XML adapter │ ├─ zwo/ → Zwift ZWO format adapter │ ├─ garmin/ → Garmin Connect API adapter │ ├─ cli/ → command-line interface │ ├─ mcp/ → MCP server for AI/LLM integration │ └─ workout-spa-editor/ → web application (https://kaiord.com/app/) ├─ docs/ → documentation ├─ LICENSE ├─ README.md └─ pnpm-workspace.yaml

🚀 Quick Start

Try the Web App

[Launch Workout Editor →](https://kaiord.com/app/)

Create and edit workouts visually in your browser. No installation required.

Use the Library

pnpm install

pnpm -r build pnpm -r test

Example usage

pnpm kaiord --help

For detailed installation instructions and usage examples, see the [Getting Started Guide](./docs/getting-started.md).

🚀 CI/CD Pipeline

Kaiord uses GitHub Actions for continuous integration and deployment:

Automated Testing: Multi-version testing on Node.js 22.x (Maintenance LTS) and 24.x (Active LTS)
Code Quality: ESLint, Prettier, and TypeScript strict mode validation
Release Automation: Changesets for version management and npm publishing
Security: Weekly dependency vulnerability audits, CodeQL static analysis, and automated dependency updates

For complete CI/CD documentation, deployment guides, and npm publishing instructions, see [Deployment](./docs/deployment.md).

Mechanical invariant guards

Beyond linting, the repo enforces its architecture and conventions with 60+ purpose-built guard scripts under scripts/, each with its own co-located test suite. They run on every commit (husky pre-commit) and in CI (pnpm test:scripts), and cover, among others:

Hexagonal architecture — layer purity, adapter isolation, and the packages/core/src/ directory allowlist (check-architecture.mjs)
Package dependency graph — every @kaiord/* dependency must match the spec table (check-package-deps.mjs)
Test conventions — should -prefixed titles and Arrange/Act/Assert structure on every test (check-test-title-should.mjs, check-test-aaa.mjs)
Privacy — no runtime values interpolated into toasts or console logs (check-no-pii-leakage.mjs)
State discipline — no Zustand store writes persistence directly (check-no-zustand-writethrough.mjs)
Spec hygiene — OpenSpec format, archive dates, and auto-generated indexes stay in sync (check-spec-format.mjs, check-archive-*.mjs)

If a rule matters here, a script enforces it — documentation describes the rules, but the guards are what make them true.

Contributing

To contribute to Kaiord:

Fork and clone the repository
Create a feature branch: git checkout -b feature/my-feature
Make your changes following the code style guidelines
Add a changeset: pnpm exec changeset (for version-worthy changes)
Test locally: pnpm -r test and pnpm -r build
Submit a PR: All checks must pass before merging

For detailed contribution guidelines, development workflow, and code standards, see [Contributing](./CONTRIBUTING.md).

📚 References & Resources

Format Specifications

Garmin FIT SDK (JavaScript) - Official FIT protocol implementation
FIT Workout Files Cookbook - Guide to encoding workout files
FIT File Types: Workout - Workout file type specification
Training Center XML (TCX) - Garmin's XML-based format
TCX Schema (XSD) - Official Garmin TCX schema definition
Zwift Workout Format (ZWO) - Zwift's XML-based workout format

❤️ Support

If you find Kaiord useful, consider supporting its development:

⭐ Star this repo to help others discover it
💖 [Sponsor on GitHub](https://github.com/sponsors/pablo-albaladejo)
☕ [Buy me a coffee](https://buymeacoffee.com/pabloalbaladejo)

Your support helps maintain and improve Kaiord for the fitness community!

Built by [Pablo Albaladejo](https://pabloalbaladejo.com)

Kaiord

概览

PopNx MCP 的三大支柱

它能帮你做什么

安装

安装之前

或者在你的电脑上运行

或者在你的电脑上运行

或者在你的电脑上运行

或者在你的电脑上运行

它能做什么

基础检查i

作者与仓库一致

仍在维护

有许可证

端点有响应

使用 OAuth 登录

工具描述中没有隐藏指令

与“诊所与健康”中的其他服务器比较i

常见问题

替代选择

Mirobody

FHIR MCP Server

Google Health MCP

作者的 README

Kaiord — Open-Source Health & Fitness Data Framework

✨ Features

Supported FIT Fields

Workout Metadata

Workout Steps

Duration Types

Known Limitations

🔒 Local-first architecture

📚 Documentation

🧩 Tech Stack

🏗 Monorepo Layout

🚀 Quick Start

Try the Web App

Use the Library

Example usage

🚀 CI/CD Pipeline

Mechanical invariant guards

Contributing

📚 References & Resources

Format Specifications

❤️ Support

📜 License