Mirobody
Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.
Descripción del creador (original en inglés)
Connect your health, fitness, nutrition, sleep, and wearable data to your AI assistant.
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
Necesitas
¿Qué app usas?
Elige tu app arriba. La recordamos, así que la próxima vez el botón dirá “Instalar en …”.
Funciona en Claude para web, escritorio y móvil:
https://wellnessproject.ai/api/mcpEjecuta esto en tu terminal
claude mcp add --transport http wellness-project https://wellnessproject.ai/api/mcpPégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"wellness-project": {
"url": "https://wellnessproject.ai/api/mcp"
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"wellness-project": {
"type": "http",
"url": "https://wellnessproject.ai/api/mcp"
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
ChatGPT solo se conecta a servidores en internet:
https://wellnessproject.ai/api/mcpLos nombres de los menús pueden variar un poco según el plan y con el tiempo.
Tu elección se guarda en una cookie en este dispositivo; no necesitas cuenta.
Esta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
Todavía no hemos leído la lista de herramientas de este servidor; revisamos los endpoints por turnos.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 6 nov 2026
El nombre en el registro se verificó con el dominio wellnessproject.ai (el registro comprueba quién es dueño del dominio)
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Aún sin revisar; revisamos los endpoints por turnos
Aún sin revisar; revisamos los endpoints por turnos
Aún sin revisar; leemos la lista de herramientas cuando revisamos el endpoint
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 1 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
El registro no indica ninguna clave obligatoria, aunque algunos servidores te piden iniciar sesión la primera vez que los usas.
Se ejecuta en la nube del creador. Te conectas por internet sin instalar nada, pero lo que envías pasa por los servidores del creador.
El repo de GitHub cambió por última vez –, y la última versión (1.2.1) llegó al registro hace 2 meses.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. Se conecta por URL, así que también funcionan las apps que aceptan servidores MCP remotos, como ChatGPT en modo desarrollador.
En la misma categoría: Mirobody, FHIR MCP Server, Google Health MCP
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
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
Privacy-first unofficial Google Health API v4 MCP server for health, sleep, activity, HR agents
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
Bring connected health and fitness data into Claude, ChatGPT, Gemini Spark, Gemini CLI, Grok, Mistral, and other MCP clients. Wellness Project is a hosted Model Context Protocol server. Your devices and logs sync into one account, and supported assistants can read or update workouts, nutrition, sleep, recovery, body metrics, goals, labs, wellbeing, and more in plain English.
This repository is the public documentation and catalog for the hosted server. It is not a self-hosted backend and contains no private server implementation.
https://wellnessproject.ai/api/mcpOnce connected, ask naturally and the assistant can call the matching Wellness Project tool:
Read tools return your logged and synced health data. Write tools add, update, or delete entries when you ask. Widget tools can render structured interactive views instead of a wall of numbers.
First create an account at https://wellnessproject.ai and connect the health sources you want under Settings → Devices. Every client below uses the same hosted endpoint:
https://wellnessproject.ai/api/mcp
Authentication is handled by OAuth. Personal API keys are not part of the current public connection flow.
https://wellnessproject.ai/api/mcp.Claude Code installs Wellness Project as a plugin. The plugin carries nothing but this server's configuration and a setup skill.
/plugin marketplace add turnnoblindeye/wellness-project-mcp
/plugin install wellness-project
Restart Claude Code, then run /mcp, select wellness-project, and authorize. There is no client ID, client secret, or API key to enter. Run /wellness-project:setup if you would rather be walked through it.
Wellness Project is listed in the official Gemini CLI Extensions Gallery. Install the extension from this public repository:
gemini extensions install https://github.com/turnnoblindeye/wellness-project-mcp
Restart Gemini CLI, then run /mcp list to check for the wellness-project server. If authentication is needed, run /mcp auth wellness-project and sign in to Wellness Project in your browser. After authorization, ask Gemini about your workouts, nutrition, sleep, recovery, or goals, or request a log update.
This connects to the hosted MCP endpoint, so no local server or personal API key is needed. Gemini CLI's OAuth flow requires a browser and access to a localhost callback. See Gemini CLI's MCP authentication documentation for details.
Cline connects to Wellness Project as a remote MCP server. Nothing is cloned, installed, or run locally.
wellness-project.https://wellnessproject.ai/api/mcp as the server URL and add it.To edit cline_mcp_settings.json directly instead:
{
"mcpServers": { "wellness-project": { "type": "streamableHttp", "url": "https://wellnessproject.ai/api/mcp", "disabled": false, "autoApprove": [] } } }
Set "type": "streamableHttp" explicitly. Cline falls back to the legacy SSE transport when the type is omitted. There is no client ID, client secret, or API key to enter. llms-install.md has the same steps written for an agent doing the setup.
ChatGPT custom MCP apps use developer mode. Current OpenAI availability is plan-dependent: full MCP support including write/modify actions is available in beta for Business, Enterprise, and Edu, while Pro can connect MCPs with read/fetch permissions in developer mode.
https://wellnessproject.ai/api/mcp as the remote MCP server.OpenAI's current setup and plan details: https://help.openai.com/en/articles/12584461
Custom MCP apps require Gemini Spark access and are added from the Gemini web app.
https://wellnessproject.ai/api/mcp and click Next.Google's current eligibility and availability rules: https://support.google.com/gemini/answer/17209137
https://wellnessproject.ai/api/mcp.Grok connector availability may depend on your Grok plan.
https://wellnessproject.ai/api/mcp.Workspace permissions may require an owner or admin to add a connector.
A short screen recording of the Wellness Project connector running inside ChatGPT:
[Watch the demo](https://github.com/turnnoblindeye/wellness-project-mcp/releases/download/v1.2.1/chatgpt-connector-demo.mp4)
Fifteen active tools render interactive views through the MCP Apps UI extension in compatible clients:
| Ask | Widget tool |
|---|---|
| "Give me a health overview" | show_health_overview |
| "How did my Fit Score look?" | show_week_fit_score |
| "Show my workouts" | show_week_workouts |
| "Show that workout" | show_workout |
| "Show my macros" | show_week_macros |
| "Show my meal diary" | show_meal_diary |
| "How's my sleep trending?" | show_week_sleep |
| "Show last night's sleep" | show_sleep_detail |
| "Steps this week?" | show_week_steps |
| "My weight trend" | show_body_weight |
| "Show my body composition" | show_body_composition |
| "Recovery trend" | show_recovery |
| "How's my running?" | show_runs |
| "How's my bench progressing?" | show_exercise_progression |
| "Show my wellbeing" | show_wellbeing |
Many trend widgets support multiple time ranges; detail widgets use the date or record relevant to the request.
The complete production-generated list of 73 advertised public tools, grouped by domain, is in [TOOLS.md](./TOOLS.md). The machine-readable descriptions, annotations, and JSON Schemas are in [catalog/tools.json](./catalog/tools.json).
Both files are generated from the same production tool registry used by tools/list. Admin-only tools and retired tools that remain callable only for older cached clients are not advertised in this catalog.
Do not edit the generated catalog by hand.
Wellness Project combines native mobile health stores, direct integrations, relay sources, and manual/chat logging.
| Source | Current support |
|---|---|
| Apple Health | Native iOS health and fitness sync |
| Google Health Connect | Native Android health and fitness sync |
| Fitbit / Google Health | Activity, sleep, heart, workout, body, and nutrition data when available |
| Oura | Sleep, readiness/recovery, heart, and activity data |
| Withings | Body, sleep, activity, heart, blood pressure, and other supported health data |
| Wyze | Supported Wyze health data |
| Hevy | Strength workout history via direct integration |
| Ultrahuman | Ring data and supported metabolic/CGM data |
| Liftosaur | Strength workout history via direct integration |
| Polar | Activity, sleep, recovery, heart, and training data |
| WHOOP | Direct integration is rolling out behind availability gating |
| Manual / chat | Workouts, meals, hydration, body metrics, labs, injuries, supplements, goals, wellbeing, and more |
Garmin, Samsung Health, Amazfit/Zepp, Coros, Wahoo, Strava, Peloton, smart scales, and other compatible sources can also reach Wellness Project through Apple Health or Health Connect when those services write the relevant data there.
Pricing below reflects the current production configuration as of September 7, 2026. Local app-store pricing may vary.
| Plan | Price | Status |
|---|---|---|
| Free Basic | $0 | Logging and editing remain free; starting October 15, 2026, Free includes 3 analysis questions per day |
| Founder Pro monthly | $4.99/month | Founder pricing through October 15, 2026 |
| Founder Pro annual | $39.99/year | Founder pricing through October 15, 2026 |
| Founder Lifetime | $199 one-time | Limited founder option, sunsetting |
| Pro monthly | $9.99/month | Standard pricing |
| Pro annual | $99.99/year | Standard pricing |
Wellness Project is informational software, not a medical product.
No. https://wellnessproject.ai/api/mcp is the hosted production server. This GitHub repository publishes documentation and schemas only.
Yes. Claude, eligible ChatGPT accounts/workspaces, Gemini Spark, Gemini CLI, Grok, Mistral, and other compatible remote MCP clients can use the same endpoint. Client-side MCP availability and permissions vary by product and plan.
Free Basic is available. Paid Founder Pro and standard Pro plans add analysis capacity and other paid capabilities; current pricing is listed above.
MCP access requires an authenticated OAuth grant and each tool operates on the
Solo se muestra el principio; lee el resto en el repo