Mirobody
Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.
作者による説明(英語の原文)
Privacy-first unofficial Polar AccessLink v4 MCP server for AI health, sleep and training agents.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
POLAR_CLIENT_ID, POLAR_CLIENT_SECRET, POLAR_REDIRECT_URI, POLAR_TOKEN_PATH, POLAR_PRIVACY_MODE, POLAR_CACHE, POLAR_CACHE_PATH, POLAR_NO_CACHE「秘密」と表示された値は、あなたのアカウントの鍵です。絶対に人に教えたり、チャットに貼り付けたりしないでください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"polarmcp": {
"command": "npx",
"args": [
"-y",
"polar-mcp-unofficial"
],
"env": {
"POLAR_CLIENT_ID": "your-value",
"POLAR_CLIENT_SECRET": "your-value",
"POLAR_REDIRECT_URI": "your-value",
"POLAR_TOKEN_PATH": "your-value",
"POLAR_PRIVACY_MODE": "your-value",
"POLAR_CACHE": "your-value",
"POLAR_CACHE_PATH": "your-value",
"POLAR_NO_CACHE": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add polarmcp --env POLAR_CLIENT_ID=your-value --env POLAR_CLIENT_SECRET=your-value --env POLAR_REDIRECT_URI=your-value --env POLAR_TOKEN_PATH=your-value --env POLAR_PRIVACY_MODE=your-value --env POLAR_CACHE=your-value --env POLAR_CACHE_PATH=your-value --env POLAR_NO_CACHE=your-value -- npx -y polar-mcp-unofficial動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"polarmcp": {
"command": "npx",
"args": [
"-y",
"polar-mcp-unofficial"
],
"env": {
"POLAR_CLIENT_ID": "your-value",
"POLAR_CLIENT_SECRET": "your-value",
"POLAR_REDIRECT_URI": "your-value",
"POLAR_TOKEN_PATH": "your-value",
"POLAR_PRIVACY_MODE": "your-value",
"POLAR_CACHE": "your-value",
"POLAR_CACHE_PATH": "your-value",
"POLAR_NO_CACHE": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"polarmcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"polar-mcp-unofficial"
],
"env": {
"POLAR_CLIENT_ID": "your-value",
"POLAR_CLIENT_SECRET": "your-value",
"POLAR_REDIRECT_URI": "your-value",
"POLAR_TOKEN_PATH": "your-value",
"POLAR_PRIVACY_MODE": "your-value",
"POLAR_CACHE": "your-value",
"POLAR_CACHE_PATH": "your-value",
"POLAR_NO_CACHE": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
POLAR_CLIENT_ID envPOLAR_REDIRECT_URI envPOLAR_TOKEN_PATH envPOLAR_PRIVACY_MODE envPOLAR_CACHE envPOLAR_CACHE_PATH envPOLAR_NO_CACHE envこの設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月7日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント davidmosiah で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
入力が必要なもの:POLAR_CLIENT_SECRET
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.3.6)がレジストリに届いたのは4 か月前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにNode.jsも必要です。
同じカテゴリには:Mirobody, FHIR MCP Server, Langcare MCP FHIR
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.
MCP server providing seamless access to FHIR APIs for AI tools and healthcare applications
An MCP FHIR server written in Go for EMR systems like Epic and Cerner
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Upgrading to 0.6.0: read the migration guide for local-only HTTP, disabled authenticated-response caching, and stricter input/profile limits.
Polar MCP
Give your AI agent your Polar Nightly Recharge, training load, PPI and HRV data — locally.
Local-first MCP server — tokens never leave your machine .
⚡ One-command install with Delx Wellness for Hermes:
npx -y delx-wellness-hermes setup— preconfigures this connector and the other 8 in a dedicated Hermes profile.
Or wire it standalone into Claude Desktop / Cursor / ChatGPT Desktop — see the install section below.
Default is stdio. Optional Streamable HTTP — no session id, JSON responses, loopback only:
npx -y polar-mcp-unofficial --http
Env: POLAR_MCP_HOST, POLAR_MCP_PORT, POLAR_MCP_TRANSPORT=http.
Local-first MCP server that connects AI agents to your Polar training, sleep, Nightly Recharge and continuous-sample data.
Unofficial project. Not affiliated with, endorsed by or supported by Polar Electro Oy. Polar is a trademark of its respective owner. Use this only with your own Polar account and in line with the Polar AccessLink API terms.
Built by David Mosiah for people who use Claude, Cursor, Hermes, OpenClaw or other MCP-compatible agents to think about training load, recovery and endurance - without copy-pasting numbers from Polar Flow.
Part of Delx Wellness, a registry of local-first wellness MCP connectors.
If this connector helps your agent workflow, please star the repo. Stars make the project easier for other AI builders to discover and help Delx keep shipping local-first wellness infrastructure.
Polar has one of the deepest training-physiology stacks among consumer wearables - Nightly Recharge, continuous samples, PPI (pulse-to-pulse intervals), training targets, sport profiles, orthostatic and fitness tests. The Polar AccessLink Dynamic API v4 exposes this data, but with 16 fine-grained OAuth scopes and a structure that's harder to navigate than typical consumer APIs.
This package handles the OAuth dance locally, normalizes responses across the v4 endpoints, redacts GPS by default, and exposes Polar through the Model Context Protocol. Tokens never leave your machine.
You'll need a Polar AccessLink client (create one here) with redirect URI http://127.0.0.1:3000/callback.
npx -y polar-mcp-unofficial setup # interactive: paste client id + secret
npx -y polar-mcp-unofficial auth # opens browser, captures the OAuth code npx -y polar-mcp-unofficial doctor # verifies you're ready
Recommended scopes (request the ones matching the data you want):
activity:read calendar:read continuous_samples:read devices:read
nightly_recharge:read ppi_data:read profile:read routes:read skin_contact:read sleep:read sports:read temperature_measurement:read tests:read training_sessions:read training_targets:read user_subscription:read
Then add this to your MCP client config:
{
"mcpServers": { "polar": { "command": "npx", "args": ["-y", "polar-mcp-unofficial"] } } }
For Claude Desktop, run setup --client claude and the snippet is written for you.
Three things to ask first:
Use polar_connection_status to check setup, then run polar_daily_summary.
Give me a 5-line training brief for today.
Call polar_weekly_summary with response_format=json. Identify my biggest
training-load/recovery bottleneck and give me a next-week plan.
Use the polar_training_load_investigation prompt, after=2026-04-01.
Walk me through my recent training sessions + Nightly Recharge.
This package uses the official Polar AccessLink Dynamic API v4. When this README says raw, it means the upstream Polar JSON for a supported endpoint - not raw device sensor streams.
| Data | Available | Notes |
|---|---|---|
| Daily activity + calendar | yes | Requires activity:read / calendar:read |
| Sleep + sleep/wake vectors | yes | Requires sleep:read |
| Nightly Recharge (recovery score) | yes | Requires nightly_recharge:read; supported devices |
| Training sessions + training targets | yes | Requires training_sessions:read / training_targets:read |
| Continuous samples (HR over time) | yes | Requires continuous_samples:read |
| PPI samples (pulse-to-pulse intervals, HRV-relevant) | yes | Requires ppi_data:read; supported devices |
| Temperature measurements | yes | Requires temperature_measurement:read; supported devices |
| Skin contact periods | yes | Requires skin_contact:read |
| Tests (fitness / orthostatic / running) | yes | Requires tests:read |
| Routes + GPS geometry | opt-in | GPS coordinates redacted unless raw mode |
| Sports + sport profiles + devices | yes | Catalog and user metadata |
| Live device telemetry | - | Not exposed by Polar AccessLink |
Start with these:
polar_quickstart - personalized 3-step setup walkthrough that adapts to what's already configuredpolar_connection_status - verify local setup, scopes and readiness before calling Polarpolar_data_inventory — inventory supported data domains, scopes, privacy modes and recommended first calls without calling Polar APIs.polar_demo - synthetic example payloads so agents see the contract before calling the real APIpolar_daily_summary - sleep, activity, Nightly Recharge and training brief for todaypolar_weekly_summary - scorecard, comparison vs prior week, next-week planpolar_wellness_context - Nightly Recharge, sleep and training load in the shared wellness_context shapeAuth & diagnostics
polar_capabilities, polar_agent_manifest, polar_privacy_audit, polar_cache_statuspolar_get_auth_url, polar_exchange_code, polar_revoke_accessAccount
polar_get_account_data, polar_list_user_devices, polar_list_subscriptionsShared wellness profile (local, never Polar data)
polar_onboarding, polar_profile_get, polar_profile_update — the Delx Wellness profile shared with the other connectors; stores only what the user typed, never tokens or biomarkersActivity & sleep
polar_list_activity, polar_list_calendarpolar_list_sleeps, polar_list_sleep_wake_vectors — sleep lists hydrate available dates with the v4 sleep-result, sleep-evaluation, and sleep-score features by defaultpolar_list_nightly_rechargeHeart & physiology (date range)
polar_heart_series — agent-safe-series/v1 bounded HR from continuous samples (prefer this for agents)polar_list_continuous_samples, polar_list_ppi_samplespolar_list_temperature_measurements, polar_list_skin_contactsTraining
polar_list_training_sessions, polar_list_training_targets, polar_list_training_target_favoritespolar_list_testsSports & routes
polar_list_sports, polar_list_sport_profile_catalog, polar_list_sport_profilespolar_get_route - GPS coordinates redacted unless raw modepolar_daily_checkin - practical daily training and recovery check-inpolar_weekly_review - review trends across activity, sleep and recoverypolar_training_load_investigation - investigate training sessions + recovery contextpolar://capabilities, polar://agent-manifest, polar://inventorypolar://summary/daily, polar://summary/weeklypolar://account-data, polar://latest/sleep~/.polar-mcp/tokens.json with 0600 permissions and are never returned by tools.POLAR_PRIVACY_MODE defaults to structured. Structured mode preserves the complete upstream physiological payload while removing secret/GPS fields; normalized aliases are additive and never replace nested v4 objects. Raw Polar JSON is opt-in via raw mode or per-call override.summary and structured modes - only raw mode exposes raw coordinates.features are validated per endpoint. Feature queries that Polar limits to one day are hydrated one available date at a time.setup writes most of these into ~/.polar-mcp/config.json (0600). Manual env override is supported:
POLAR_CLIENT_ID=<client-id>
POLAR_CLIENT_SECRET= POLAR_REDIRECT_URI=http://127.0.0.1:3000/callback
POLAR_SCOPES="activity:read calendar:read continuous_samples:read ..." POLAR_PRIVACY_MODE=structured # summary | structured | raw POLAR_CACHE=sqlite # no effect: authenticated responses are never cached POLAR_TOKEN_PATH=~/.polar-mcp/tokens.json POLAR_CACHE_PATH=~/.polar-mcp/cache.sqlite
npx -y polar-mcp-unofficial setup --client hermes --no-auth
npx -y polar-mcp-unofficial auth # run locally if browser auth is needed npx -y polar-mcp-unofficial doctor --client hermes hermes mcp test polar
After Hermes config changes, use /reload-mcp or hermes mcp test polar. Don't restart the gateway for normal data access.
If browser OAuth has to happen on a different machine than Hermes, run auth locally and copy ~/.polar-mcp/tokens.json to the server with chmod 600.
http://127.0.0.1:3000/callbackgit clone https://github.com/davidmosi冒頭だけを表示しています。続きはリポジトリで読めます