# Memory.fit

> Memory.fit is an MCP server for knowledge and memory. Connect your watch, sleep and meals to ChatGPT or Claude so it can plan your training week. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Platforms:** iOS, Android, API
- **Website:** https://memory.fit
- **Repository:** https://github.com/fun-management-srl/memory-fit-mcp
- **MCP Registry name:** fit.memory/memory-fit
- **Categories:** [knowledge and memory](https://ai-powered.com/categories/knowledge-and-memory), [health and science](https://ai-powered.com/categories/health-and-science)
- **Listing updated:** 2026-11-18

## About

Memory.fit is a hosted server, so there is nothing to build; an account set up in its iPhone and Android app comes first. Sign-in is OAuth 2.1, and clients without OAuth can use a personal key from the app. Its README lists setup for Claude, ChatGPT, Grok, Cursor, Claude Code, Codex, Gemini CLI and Cline.

The assistant can read workouts from Garmin, Wahoo, COROS, Polar, Suunto, Apple Health, Health Connect and more, plus sleep, HRV, resting heart rate, body composition, food and drink, and your races and goals. With permission it writes training sessions that go to your watch as structured workouts with targets in your own zones, daily targets, meal plans, logged meals and notes for your other assistants. A get_updates call returns only what has arrived since it last looked.

Memory.fit recommends nothing itself: the plans come from your assistant and the data stays yours. It is not medical advice. The connection settings in the repository are MIT licensed, while the server and app are not.

## Features

- **Reads your training data:** Workouts, sleep, HRV, resting heart rate, body composition and meals.
- **Plans reach your watch:** Planned sessions go to the watch as structured workouts in your zones.
- **Fuel planning:** Meal plans and fueling for long sessions can be saved to the app.
- **Incremental check-ins:** get_updates returns only new data since the last look.
- **Notes between assistants:** Leave notes that your other AIs can read.
- **Wide device support:** Connects Garmin, Apple Health, Strava, Oura, WHOOP, COROS, Polar and others.

## Good for

- Plan a 12-week build toward a race
- Review a session against the plan
- Set a lighter week when life gets busy
- Plan fuel and drinks for a long ride
- Keep one training memory across several AI assistants

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http memory-fit https://api.memory.fit/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://api.memory.fit/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "memory-fit": {
      "url": "https://api.memory.fit/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "memory-fit": {
      "type": "http",
      "url": "https://api.memory.fit/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "memory-fit": {
      "serverUrl": "https://api.memory.fit/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "memory-fit": {
      "type": "http",
      "url": "https://api.memory.fit/mcp"
    }
  }
}
```

## Tools

- `get_updates`: Return only the data that arrived since the last check

## FAQ

### How do I sign in?

OAuth 2.1 with dynamic client registration; a personal key from the app works as a Bearer header for clients without it.

### Do I need an account first?

Yes. A Memory.fit account must be set up in the app before connecting.

### Does Memory.fit give medical advice?

No. It recommends nothing itself; the plans are the AI's and it is not medical advice.

### Which assistants are supported?

Claude, ChatGPT, Grok, Cursor, Claude Code, Codex, Gemini CLI, Cline and any MCP client.

### How do I add Memory.fit to Claude Code?

Run this command in your terminal: claude mcp add --transport http memory-fit https://api.memory.fit/mcp

### What are the best alternatives to Memory.fit?

The closest alternatives to Memory.fit are Codebase Memory, XERJ, Claude Code Ultimate Guide, Tooluniverse and Nautilus Compass Memory.

## Where this comes from

- Description: written from the project's README and the project's website.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Tooluniverse](https://ai-powered.com/mcp/tooluniverse): Tooluniverse is an open-source MCP server for health and science.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [Oya Browser](https://ai-powered.com/mcp/oya-browser): Oya Browser is a freemium MCP server for browser automation.
- [NeuroStack](https://ai-powered.com/mcp/neurostack): NeuroStack is a freemium MCP server for knowledge and memory.
- [BasalFit](https://ai-powered.com/mcp/basalfit): BasalFit is a free MCP server for health and science.

---
Source: https://ai-powered.com/mcp/memory-fit
