TrainingPeaks icon

TrainingPeaks MCP

TrainingPeaks in ChatGPT, Claude and every MCP app.

TrainingPeaks has no official MCP server.

Memory.fit is a hosted MCP server for athletes: connect TrainingPeaks in the Memory.fit app, add one address to your AI, and it reads planned sessions by date, sport and title, planned duration.

You need the Memory.fit app on Android (the iPhone app is coming), and an AI that can add a custom connector.

The address to add to your AI

https://api.memory.fit/mcp?src=mcp-trainingpeaks
Get it onGoogle PlayComing soon onApp Store
Set it up

TrainingPeaks and your AI, in short

Official TrainingPeaks MCP
None
Memory.fit
Hosted MCP server, nothing to install
Your AI reads
Planned sessions by date, Sport and title, Planned duration
Workouts to TrainingPeaks
No
Works in
ChatGPT, Claude, Gemini, Grok Bot and any MCP app
Price
$9 a month or $69 a year, with 7 days free

Checked October 28, 2026.

What your AI reads

What your AI can read from TrainingPeaks

Once TrainingPeaks is connected in the Memory.fit app, every AI you add reads the same history, under its own permissions.

  • Planned sessions by date
  • Sport and title
  • Planned duration
  • Planned TSS and intensity factor
  • Your coach's description

The tools that read it:get_workoutsget_training_planget_day

Setup

Set up TrainingPeaks in your AI

1. In the Memory.fit app

  1. 01In TrainingPeaks, open Settings → Calendar and copy your iCal link.
  2. 02In the Memory.fit app, open Settings → Health data → TrainingPeaks.
  3. 03Paste the link and tap Connect.
  4. 04Memory.fit checks your calendar every hour. Moved or removed sessions follow.

2. In your AI

Pick your AI. Each one signs in with your Memory.fit account.

ClaudeAny plan · about a minute
Install in Claude
  1. 01Install in Claude
  2. 02Tap Add, then sign in to Memory.fit
  3. 03In a chat, turn on Memory.fit under + › Connectors

Claude adds new connectors on the web or desktop. On a phone, use a computer once, and after that it works in the Claude app too.

Every step for Claude
ChatGPTOn a computer · about 2 minutes
  1. 01On chatgpt.com, open Plugins and tap +, then Add custom MCP server
  2. 02Name it Memory.fit and paste the address
  3. 03Choose OAuth, confirm the warning, then Create as a plugin and sign in
  4. 04In a new chat, type @ and pick Memory.fit

The address: https://api.memory.fit/mcp?src=mcp-trainingpeaks

Coming soon: one tap from ChatGPT's plugin directory.

Every step for ChatGPT
GeminiGemini Spark (Google AI Pro or Ultra), a personal Google account, US
  1. 01On gemini.google.com: Settings › Connected Apps
  2. 02Under Custom apps, tap Add a custom app
  3. 03Paste the address, tap Next, then sign in to Memory.fit
  4. 04In a chat, type @ and pick Memory.fit

The address: https://api.memory.fit/mcp?src=mcp-trainingpeaks

Every step for Gemini
Grok BotComes with higher SuperGrok and Cursor plans
  1. 01In the Memory.fit app, open Settings → AI agents → Grok Bot and copy your Memory.fit link.
  2. 02Open Grok Bot on your computer or phone and message any of your Bots.
  3. 03Send “Add a custom MCP server called Memory.fit at” and paste your Memory.fit link.
  4. 04Check the name and link it shows you, then approve it.
  5. 05Tap Authorize and sign in with your Memory.fit account. Memory.fit works from your next message.

The address: https://api.memory.fit/mcp?src=mcp-trainingpeaks

Every step for Grok Bot
GrokAbout a minute
  1. 01Copy the address
  2. 02On grok.com: Connectors › New connector › Custom
  3. 03Paste it, then sign in to Memory.fit

The address: https://api.memory.fit/mcp?src=mcp-trainingpeaks

Every step for Grok
Cursor
  1. 01In the Memory.fit app, open Settings → AI agents → Cursor and create your key.
  2. 02Add the block to ~/.cursor/mcp.json (or .cursor/mcp.json in a project).
  3. 03Check Cursor Settings → Tools & MCP shows Memory.fit as connected.
{
  "mcpServers": {
    "memory-fit": {
      "url": "https://api.memory.fit/mcp?src=mcp-trainingpeaks",
      "headers": { "Authorization": "Bearer mem_pat_your_key" }
    }
  }
}

Cursor connects with a key from the Memory.fit app. Paste it into Cursor's settings, never into a chat.

Every step for Cursor
Claude CodeOn a computer · Claude Code · a minute
  1. 01In your terminal, run the command
  2. 02Start Claude Code and run /mcp
  3. 03Pick memory-fit and sign in to Memory.fit
claude mcp add --transport http memory-fit "https://api.memory.fit/mcp?src=mcp-trainingpeaks"
Every step for Claude Code
CodexOn a computer · Codex CLI · a minute
  1. 01In your terminal, run the command
  2. 02Then run: codex mcp login memory-fit
  3. 03Sign in to Memory.fit in the browser that opens
codex mcp add memory-fit --url "https://api.memory.fit/mcp?src=mcp-trainingpeaks"
Every step for Codex

Try it

Try these prompts

“Read the sessions my coach planned for next week and tell me which days need the most fuel.”

Uses:get_workoutsget_day

“Write a fueling plan for Saturday's long ride from my coach's plan.”

Uses:get_workoutsset_session_fuel_plan

“Compare what my coach planned last week with what my watch recorded.”

Uses:get_workoutsget_trends

“Plan my meals around the two key sessions this week.”

Uses:get_workoutsset_meal_plan

Your options

Every way to get TrainingPeaks into an AI

TrainingPeaks runs no MCP server. Community servers run on your own computer, hosted services run it for you, and so does Memory.fit.

OptionWhat you need
Community serverJamsusMaximus/trainingpeaks-mcpOn your own computerA cookie copied from a browser signed in to TrainingPeaks, run on your own computer.
Community serverbkohler/trainingpeaks-mcp-devOn your own computerThe same browser cookie, which expires after a few weeks, run on your own computer.
Hosted serviceAthleteDataHostedAn AthleteData account.
Hosted MCP serverMemory.fit MCPHosted, in ChatGPT, Claude, Gemini, Grok Bot and any MCP appThe Memory.fit app with TrainingPeaks connected. $9 a month or $69 a year, with 7 days free.

When another option is better

  • You are a developer approved for TrainingPeaks' partner API: build on it directly.

Limits, said plainly

  • The calendar link carries planned sessions only. Completed workouts come from your watch, Apple Health or Health Connect.
  • Memory.fit checks your TrainingPeaks calendar every hour, so a moved session follows within the hour.
  • TrainingPeaks' partner API is for approved developers only, and no official TrainingPeaks MCP exists.
  • For your AI's own sessions on a calendar and your watch, connect intervals.icu or your watch to Memory.fit.

Sources, checked October 28, 2026

Questions

TrainingPeaks MCP, in short.

  • No. TrainingPeaks does not run an MCP server. Community servers exist, and they run on your own computer.

  • Yes. Connect TrainingPeaks in the Memory.fit app, add Memory.fit to ChatGPT as a connector, and ChatGPT reads it. Claude and every MCP app work the same way.

  • No. Memory.fit is hosted: you add one address to your AI and sign in with your Memory.fit account. Nothing to install, no password of another service to paste.

  • Each AI gets only the permissions you allow, every change shows in the app with who made it, and you can disconnect an AI or a source at any time.

  • The calendar link only reads your TrainingPeaks plan. To get the sessions your AI plans onto a calendar and your watch, connect intervals.icu, Garmin, COROS, Suunto or Wahoo in the Memory.fit app.

Related

More MCP pages

TrainingPeaks is a trademark of TrainingPeaks, LLC. Memory.fit is not made by or affiliated with TrainingPeaks, LLC.

Your next chapter starts with everything you've learned.

On Android now. iPhone is coming: join the waitlist and we'll email you the day Memory.fit is on the App Store.

No spam. One email when it's ready.

Get it onGoogle PlayComing soon onApp Store