Connect Claude Code with Tredict

FAQ

LLMs are artificial systems that make mistakes and are no substitute for a trainer or your own mind.

To connect Claude Code to the ‘Tredict MCP Server’, follow these instructions.

Add the MCP server to Claude Code

Open a terminal and run the following command to add the Tredict MCP server to Claude Code:

claude mcp add --transport http tredict https://www.tredict.com/api/mcp/v2

Start Claude Code in the terminal and enter the command /mcp to check the connection status.

If you are not connected, you will see the following:

❯ claude.ai Tredict · ✘ failed

Select the Tredict entry and confirm the action authenticate. A browser window will open and you can follow the authentication process, which will take you back to the terminal. If this does not work, you can also connect to the MCP server directly via Claude Web. The connection will then also appear in Claude Code. To do this, follow the instructions in the Tredict FAQ for the Connection via Claude Web. If you are connected via the web, restart your Claude terminal for the changes to take effect. If everything went well, you will now see:

❯ claude.ai Tredict · ✔ connected

OAuth client credentials for Claude

You should provide these “OAuth Client Credentials” when you are asked for them.:

OAuth Client ID: claude
OAuth Client Secret: You can simply leave this field blank.

Example prompts with Claude Code

Now you can use the ‘Tredict MCP Tools’ directly in Claude Code. Just get started by typing /tredict in the Claude Terminal prompt to see a list of available tools and prompts.

Find detailed descriptions of the tools, prompts and resources of the "Tredict MCP Server" here: Tredict MCP Server Documentation.

Example prompts:

/claude.ai Tredict:create-plan (MCP)
Claude will guide you through the right questions and steps to create a comprehensive training plan for you!

/claude.ai Tredict:better-names (MCP)
Set better training titles and descriptions for your completed activities.

/claude.ai Tredict:coolest-training (MCP)
Displays your most impressive workout based on your training history.

/claude.ai Tredict:determine-ftp (MCP)
Determine your current FTP (Functional Threshold Power) based on your training history.

Further information on configuring Claude Code can be found in the Documentation by Claude Code.

Example: Creating a training plan with Claude Code

In Claude Code, a training plan for running is created in Tredict.

Claude Code Terminal has loaded the Tredict plan creation tool and a training plan for running is created directly in Tredict.

↓

4-Week Beginner Running: Base & Build (created by Claude Code)

Visit training plan created by Felix Gertz

The resulting training plan, which was created directly in Tredict with the help of Claude Code.
Click on it to view it in detail.

What is the Tredict MCP Server?

The Tredict MCP Server enables the integration of AI-supported training planning and analysis directly into your preferred AI environment. With a variety of tools, you can analyse your training data, create individual training plans and optimise your athletic performance. The server provides access to detailed activity data, capacity values, zone distributions and much more to generate tailored training recommendations with the help of an LLM and AI. Whether you are an ambitious runner, cyclist or swimmer, the Tredict MCP Server helps you evaluate your endurance sports training data even more efficiently.

With the Tredict MCP Server, you integrate Tredict into the AI, not the AI into Tredict. Full control and GDPR compliant? Of course!

Next question:Connect ChatGPT with Tredict Previous question:Connect Claude Web with Tredict Overview:View all questions