Real workflows, in real training
MCP workflows for endurance sports
Real integrations with LLMs and sports data. No theory, just working setups.
MCP for the protocol. Run for the sport. Book for the metrics.
Featured workflow
I let Claude plan my running comeback after six weeks off
After two colds in six weeks I used Claude and the Tredict MCP Server to get back into running. I was sceptical. After two weeks I was not.
Read →Start here
-
01
What the Tredict MCP Server actually gives Claude or ChatGPT
A technical look at what data and actions Claude or ChatGPT can work with through the Tredict MCP Server, and why that changes what AI can do with training data.
-
02
Connect Tredict to Claude, ChatGPT, Codex and Mistral via MCP
How to connect the Tredict MCP Server to Claude, ChatGPT, Codex and Mistral. Which client works best and why.
-
03
Why AI training plans usually fail, and when they do not
Same data, same prompt, three AI assistants. Why ChatGPT and Mistral fail at training plans and what makes the difference.
Why this site exists
MCP makes it possible to connect AI directly to real endurance sports training data. These are the workflows I actually use, built around Tredict and tested over weeks of real training.
All posts
-
Building a reusable training plan library with AI that syncs
How endurance coaches use AI assistants like Claude and Perplexity with the Tredict MCP Server to build a reusable training plan library that syncs structured workouts to Garmin, Coros and other watches.
-
Using Perplexity's Custom Connector to Analyse Endurance Training Data
Perplexity as MCP client connects to external tools. See how it works with Tredict to analyse running data, determine FTP, and answer training questions with real-time web context.
-
Ground contact time is speed-dependent. Here is how to normalize it.
Raw ground contact time numbers are misleading because GCT drops at higher speeds. Claude calculated a normalized efficiency value from my actual training data via the Tredict MCP Server.
-
Interactive MCP Apps render real UI inside Claude and ChatGPT
A working example of Interactive MCP Apps, also known as ChatGPT Apps on the OpenAI side. Tredict ships two MCP tools that render actual widgets inside Claude.ai and ChatGPT, not plain text summaries.
-
Claude Code with Tredict: long-running plan creation without the hangs
Claude.ai is great for day-to-day training questions. Claude Code in the terminal is built for long-running tasks, which turns out to matter a lot when you want a full season plan written directly into Tredict.
-
Why AI training plans usually fail, and when they do not
Same data, same prompt, three AI assistants. Why ChatGPT and Mistral fail at training plans and what makes the difference.
-
Connect Tredict to Claude, ChatGPT, Codex and Mistral via MCP
How to connect the Tredict MCP Server to Claude, ChatGPT, Codex and Mistral. Which client works best and why.
-
What the Tredict MCP Server actually gives Claude or ChatGPT
A technical look at what data and actions Claude or ChatGPT can work with through the Tredict MCP Server, and why that changes what AI can do with training data.
-
I let Claude plan my running comeback after six weeks off
After two colds in six weeks I used Claude and the Tredict MCP Server to get back into running. I was sceptical. After two weeks I was not.