Connect Claude Web with Tredict

FAQ

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

Follow these steps to connect Claude.ai Web to the ‘Tredict MCP Server’ and the ‘Tredict MCP App’.

Add the Tredict connector to Claude Web

Go to "Customise -> Connectors" in the Claude web interface or click on this link: Claude Connectors.

Under ‘Connectors’, click on the "Plus Button" and then select "Add custom connector" from the drop-down menu.

A modal window with the settings opens.

Add Tredict MCP connector to Claude Web.

The MCP connector fields for Tredict in Claude Web.

Fill in the fields in the modal as follows:

Name: Tredict

Remote MCP Server URL: https://www.tredict.com/api/mcp/v2

Click on "Advanced settings" and enter the following OAuth credentials:

OAuth Client ID: claude

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

Click on the "Add" Button to start the OAuth2 flow. You will be redirected to the Tredict authorisation page and, after successful authentication, back to the Claude web interface.

You are now connected! Click on the Tredict connector to see all available tools and permissions and set them as needed. "Always allow" can be selected to ensure everything runs smoothly.

Choose from ready-made prompts

In the ‘Claude Chat’ input field, you can now select ready-made prompts from Tredict by clicking on ‘Add from Tredict’. These prompts guide you through a query of parameters that are relevant to a prompt, helping you to better specify a request to Claude.

Select the Tredict MCP connector in Claude Web.

Ready-made prompts provided to Claude.ai Web by the Tredict MCP tools.

Example prompts to Claude Web

Now you can use the ‘Tredict MCP Tools’ directly in Claude Web, for example with these prompts:

"Take a close look at yesterday's interval training and use it to create a new structured workout for me in a reusable training plan in Tredict."

"Analyse my training history and determine my functional threshold power (FTP) for cycling."

"Create a 4-week running training plan in Tredict. Analyse my performance and training history beforehand so that you can get an idea of my fitness level."

"Show me my best training session from last month."

"Find training sessions without good titles, analyse them, and set better titles and descriptions in Tredict."

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

Example video: Reproduce an executed workout in a new structured workout

Claude analyses a completed long interval training session and, based on this activity, creates a reusable structured workout in Tredict, which is then displayed in the Tredict MCP app.

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 Claude Code with Tredict Previous question:Tredict API - Connect your platform or application Overview:View all questions