# OpenAthlete (MCP server)

> OpenAthlete is an MCP server that adds cloud and DevOps tools to AI assistants such as Claude Code, Cursor and VS Code. Endurance training: activities, load, zones, and workouts sent to Garmin, COROS and Suunto watches. It has 141 GitHub stars, is released under the AGPL-3.0 license and runs as a remote server at https://api.openathlete.org/mcp.

Serious endurance training. Without the subscription. The open-source training platform for runners, trail runners, triathletes, cyclists and their coaches.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/openathleteorg/openathlete |
| GitHub stars | 141 |
| License | AGPL-3.0 |
| Language | TypeScript |
| Transport | streamable-http |
| Packages | none (remote only) |
| Remote URL | https://api.openathlete.org/mcp |
| Needs API key | no |
| Official | yes |
| Works with | Claude Code, Cursor, VS Code, Claude.ai, ChatGPT |
| Category | Cloud & DevOps |
| Latest release | v1.6.0 (Nov 12, 2026) |
| Last commit | Nov 16, 2026 |
| MCP registry name | org.openathlete/mcp |

## Install

### Claude Desktop

```
Settings > Connectors > Add custom connector
URL: https://api.openathlete.org/mcp
```

Remote servers are added as a custom connector, not in claude_desktop_config.json.

### Claude Code

```sh
claude mcp add --transport http openathlete "https://api.openathlete.org/mcp"
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "openathlete": {
      "url": "https://api.openathlete.org/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "openathlete": {
      "type": "http",
      "url": "https://api.openathlete.org/mcp"
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Similar MCP servers

- [Prometheus MCP Server](https://appsgit.com/mcp-servers/prometheus-mcp-server-prometheus): An API-complete MCP server to manage Prometheus-compatible backends. (142 stars, Apache-2.0, official)
- [DigitalOcean](https://appsgit.com/mcp-servers/digitalocean): Build, deploy, manage, and troubleshoot applications and infrastructure on DigitalOcean. (138 stars, MIT, official)
- [Evalview MCP](https://appsgit.com/mcp-servers/evalview-mcp): Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude. (142 stars, Apache-2.0)
- [MCP Ts Template](https://appsgit.com/mcp-servers/mcp-ts-template): TypeScript template for building MCP servers with declarative tooling, observability, and auth. (154 stars, Apache-2.0)
- [Magg](https://appsgit.com/mcp-servers/magg): Aggregates and proxies other MCP servers, letting LLMs discover, add, and manage tools at runtime. (143 stars, AGPL-3.0)
- [SigNoz MCP Server](https://appsgit.com/mcp-servers/signoz-mcp-server): SigNoz MCP server: access metrics, traces, logs, alerts, and dashboards via AI assistants. (132 stars, Apache-2.0, official)

---

Canonical page: https://appsgit.com/mcp-servers/openathlete
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed daily.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.
