# Tredict

Connects an AI assistant to your Tredict training history: activity breakdowns, threshold estimates, and structured plans pushed to your watch.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 2
- Author: tredict-com
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/tredict-com/mcp-server
- Updated: 2026-04-18
- HTML: https://affpapa.org/en/nevibecode/mcp/tredict

## What it does

Tredict is a planning and analytics platform for endurance athletes — running, cycling, swimming, strength work. This MCP server hands your assistant the training archive: per-activity metrics plus full time series for heart rate, pace, power, cadence, altitude, position and laps. It also derives FTP, running FTPace, HRmax and lactate threshold from recent efforts.

The tool set splits into reading and writing. `plan-creation` builds a reusable multi-week plan under “My Plans”, `add-plan-training` appends one structured workout to an existing plan, and `planned-workout-change-date` moves a scheduled session. You also get HRV, sleep, body values and resting heart rate, zone revisions per sport and zone type, and equipment lists with distance and duration. Plans placed on the calendar are uploaded to connected watches, among them Garmin, Suunto, Coros, Wahoo and Apple Watch.

Transport is Streamable HTTP and SSE, with OAuth 2.1 plus PKCE or a personal API token. The token route matters for clients that skip OAuth: create one under “Settings → Personal API / MCP” and send it as a bearer token. Scopes are narrow — `activityRead`, `activityWrite`, `bodyvaluesRead` — so an assistant without `activityWrite` cannot touch your plans or create new ones.

## Requirements
- Remote server: `https://www.tredict.com/api/mcp/v2`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp-server https://www.tredict.com/api/mcp/v2
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add tredict --url https://www.tredict.com/api/mcp/v2
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "tredict": {
            "url": "https://www.tredict.com/api/mcp/v2"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "tredict": {
            "type": "http",
            "url": "https://www.tredict.com/api/mcp/v2"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http tredict https://www.tredict.com/api/mcp/v2
```

## When to use it
- break down a long run by laps and zones
- build a multi-week plan for a target race
- estimate running FTPace from recent intervals
- compare prescribed zones against what you actually ran
- check how far your current shoes have gone

## Example prompts
- How did my long run on Sunday go?
- Build me a 10-week half marathon plan from my recent training
- What is my current running FTP?

## Similar
- [google-analytics](https://affpapa.org/en/nevibecode/skills/google-analytics.md) — skill · 520 installs
- [connector-googledrive](https://affpapa.org/en/nevibecode/skills/connector-googledrive.md) — skill · 9100 installs
- [connector-spotify](https://affpapa.org/en/nevibecode/skills/connector-spotify.md) — skill · 6500 installs
- [configuring-connections](https://affpapa.org/en/nevibecode/skills/configuring-connections.md) — skill · 2900 installs
- [build-zoom-phone-integration](https://affpapa.org/en/nevibecode/skills/anthropics-build-zoom-phone-integration.md) — skill · 2100 installs
- [debug-zoom](https://affpapa.org/en/nevibecode/skills/anthropics-debug-zoom.md) — skill · 2100 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md