# enduraw-MCP

MCP server for [Enduraw](https://app.enduraw.co). Connects directly to Enduraw's official APIs to access your physiological Runner Matrix, Critical Speed, cardio efficiency, climbing/downhill biomechanics, official race database (329+ races), 3D course elevation profiles, aid station checkpoints, and training history from Claude Code, Claude Desktop, Cursor, Windsurf, Antigravity, or any MCP client.

24 tools across 7 categories:
- Profile and Runner Matrix (5 tools)
- Athlete Lab and Modeling (3 tools)
- Physiological Tests and Evaluations (5 tools)
- Activities and Deep In-Session Analysis (5 tools)
- Race Database, Elevation Profiles and Pacing Plans (4 tools)
- Form and Fatigue (1 tool)
- Notifications and Daily Alerts (1 tool)

---

## Requirements

- Node.js 20+
- An Enduraw account ([app.enduraw.co](https://app.enduraw.co)) with your session access token.

---

## Installation

### Claude Code

```bash
claude mcp add enduraw -e ENDURAW_ACCESS_TOKEN=your_jwt_token -- npx -y github:ploa33/enduraw-MCP
```

### Claude Desktop

Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):

```json
{
  "mcpServers": {
    "enduraw": {
      "command": "npx",
      "args": ["-y", "github:ploa33/enduraw-MCP"],
      "env": {
        "ENDURAW_ACCESS_TOKEN": "your_jwt_token"
      }
    }
  }
}
```

### Cursor

Add to `.cursor/mcp.json` in your project root or Cursor MCP settings:

```json
{
  "mcpServers": {
    "enduraw": {
      "command": "npx",
      "args": ["-y", "github:ploa33/enduraw-MCP"],
      "env": {
        "ENDURAW_ACCESS_TOKEN": "your_jwt_token"
      }
    }
  }
}
```

### Windsurf

Add to `~/.codeium/windsurf/mcp_config.json`:

```json
{
  "mcpServers": {
    "enduraw": {
      "command": "npx",
      "args": ["-y", "github:ploa33/enduraw-MCP"],
      "env": {
        "ENDURAW_ACCESS_TOKEN": "your_jwt_token"
      }
    }
  }
}
```

### Antigravity

Add to `~/.gemini/config/mcp_config.json`:

```json
{
  "mcpServers": {
    "enduraw": {
      "command": "npx",
      "args": ["-y", "github:ploa33/enduraw-MCP"],
      "env": {
        "ENDURAW_ACCESS_TOKEN": "your_jwt_token"
      }
    }
  }
}
```

### Any MCP Client

Run the server directly with your environment variable:

```bash
ENDURAW_ACCESS_TOKEN=your_jwt_token npx -y github:ploa33/enduraw-MCP
```

The server communicates over stdio using the Model Context Protocol.

---

## Authentication

To connect to Enduraw, you need your `ENDURAW_ACCESS_TOKEN` (JWT session token):

1. Log into your account on [app.enduraw.co](https://app.enduraw.co).
2. Open your browser Developer Tools (F12 or right-click > Inspect).
3. Go to the Application (Chrome/Brave/Edge) or Storage (Firefox) tab.
4. Under Cookies, select `https://app.enduraw.co`.
5. Find the cookie named `access_token` and copy its full value.
6. Paste it as the `ENDURAW_ACCESS_TOKEN` environment variable in your configuration.

---

## Available Tools (24 Tools)

### 1. Profile and Runner Matrix (5 tools)

| Tool | Parameters | Description |
|---|---|---|
| `get_enduraw_athlete_profile` | None | Athlete biometrics (weight, height, age), Strava connection status, and plan entitlements |
| `get_enduraw_matrix` | None | Complete Runner Matrix (global volume, key sessions, cohort percentiles, terrain stats) |
| `get_enduraw_matrix_summary` | None | Compact summary of Runner Matrix scores and key indicators |
| `get_enduraw_matrix_history` | None | Historical progression and chronological evolution of Runner Matrix scores |
| `get_enduraw_archive_status` | None | Status of the activity/FIT archive processing pipeline |

### 2. Athlete Lab and Modeling (3 tools)

| Tool | Parameters | Description |
|---|---|---|
| `get_enduraw_athlete_lab` | None | Complete synthesis of the 5 performance pillars, critical speed model, and cohort percentiles (tab=modeling) |
| `get_enduraw_pillar_deep_dive` | `pillar` (enum: endurance, resilience, uphill, downhill, physiology, all) | Granular deep dive into physiological pillars (climbing duration, downhill VDM, cardiac decoupling, resilience calendar) |
| `get_enduraw_performance_profile` | None | Critical Speed (Vc, D', benchmark times), radar scores (0-100 on 6 dimensions), and race format ratings |

### 3. Physiological Tests and Evaluations (5 tools)

| Tool | Parameters | Description |
|---|---|---|
| `get_enduraw_physio_tests` | None | Physiological evaluation hub: lab test catalogue (Flat, Incline, Lactate) and athlete's real computed benchmarks |
| `get_enduraw_cardio_efficiency` | `min_speed_kmh` (optional), `max_speed_kmh` (optional) | Cardiac cost of pace across 66 speed bands with median HR, Q25/Q75 dispersion, and post-effort recovery kinetics |
| `get_enduraw_slope_and_cadence` | None | Climbing/downhill biomechanics, VAM (m/h) and cadence (spm) broken down by gradient percentage (-25% to +25%) |
| `get_enduraw_cardio_zones` | None | Karvonen heart rate zones (Z1 to Z5), threshold BPMs, and total training hours/shares spent in each zone |
| `get_enduraw_records_progression` | `distance` (optional: 1k, 5k, 10k, 15k, semi, 30k, marathon) | Historical personal records and progression curves for benchmark distances with milestones |

### 4. Activities and Deep In-Session Analysis (5 tools)

| Tool | Parameters | Description |
|---|---|---|
| `get_enduraw_activities` | `limit` (default: 10), `period` (optional: 52w, all, 12w, 4w), `analyzed_only` (optional boolean) | Synced activities with weather conditions (temperature, wind), duration, distance, and analysis readiness |
| `get_enduraw_activity_analysis` | `activity_id` (number, required) | Deep session analysis: physiological storyline, quality score, heart rate zone distribution, and efficiency metrics |
| `get_enduraw_activities_stats` | None | Global activity volume statistics over 52 weeks or lifetime (total distance, observed vs estimated moving time, session count) |
| `get_enduraw_activities_map` | None | Complete GPS coordinates array of all activities for personal Heatmap mapping |
| `get_enduraw_analysis_quota` | None | Consult current monthly/annual deep-analysis quota and subscription level |

### 5. Race Database, Elevation Profiles and Pacing Plans (4 tools)

| Tool | Parameters | Description |
|---|---|---|
| `get_enduraw_pacing_plans` | None | Active and upcoming race pacing and nutrition plans, including available plan credits |
| `get_enduraw_races` | `query` (optional string) | Official race course database (329+ races: UTMB, CCC, Saintelyon, Diagonale des Fous, etc.) |
| `get_enduraw_race_course_profile` | `race_name` (string, required) | Full 3D elevation profile of an official race with D+, D-, min/max altitude, and aid stations count |
| `get_enduraw_race_gpx` | `race_name` (string, required) | Full GPX GeoJSON track and official checkpoints/aid stations with exact distances and cumulative elevation |

### 6. Form and Fatigue (1 tool)

| Tool | Parameters | Description |
|---|---|---|
| `get_enduraw_form_fatigue` | `days` (default: 180), `sport` (default: 'all') | Official Enduraw Form and Fatigue modeling (CTL, ATL, TSB curves) directly from `/auth/api/activities/form-fatigue/`. Returns official metrics or subscription requirement status (Starter tier) |

### 7. Notifications (1 tool)

| Tool | Parameters | Description |
|---|---|---|
| `get_enduraw_notifications` | `today` (optional YYYY-MM-DD) | Daily activity notifications, processing alerts, and training updates |

---

## Example Prompts

Here are examples of prompts you can use once connected:

- "What is my Critical Speed (Vc) and D' according to Enduraw, and what are my theoretical times on 5k and 10k?"
- "Analyze my cardiac cost between 10 km/h and 13.5 km/h. How many beats does each km/h cost me?"
- "Extract the full 3D course elevation profile and official checkpoints for the CCC."
- "Show me all 20 aid stations on the UTMB with their exact kilometer markers and cumulative elevation gain."
- "What is my climbing VAM profile on 10% vs 20% slopes, and at what gradient does my cadence drop?"
- "Show me my progression curve on the Half-Marathon and Marathon benchmark distances."
- "What is the breakdown of continuous climbs in my Athlete Lab (<5 min to 20+ min) and my downhill descent speed (VDM)?"

---

## Development

Clone and test locally:

```bash
git clone https://github.com/ploa33/enduraw-MCP.git
cd enduraw-MCP
npm install
```

Copy the example environment file:

```bash
cp .env.example .env
# Edit .env with your ENDURAW_ACCESS_TOKEN
```

Run locally:

```bash
npm start
```

---

## Disclaimer

This project is an independent, community-developed open-source tool built for personal interoperability purposes using the Model Context Protocol. It is not affiliated with, maintained by, authorized by, endorsed by, or sponsored by Enduraw or any of its subsidiaries. All product names, trademarks, and registered trademarks belong to their respective owners.

---

## License

MIT