SkillAgentSearch skills...

Threshold

Garmin MCP server: connect Garmin Connect to Claude, ChatGPT and any AI. Readiness, HRV, training load, FIT analysis. Free on Cloudflare Workers.

Install / Use

claude mcp add KareemmSayed -- npx -y github:KareemmSayed/Threshold

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

84/100

Supported Platforms

Claude Code
Claude Desktop

Tags

Our assessment of Threshold

Threshold scores 84/100 on our quality scale, 606th of 950 AI & Machine Learning skills we index.

Its MCP Server is 27 KB long, well organised into 27 sections with 10 code examples: a thorough specification that gives an agent plenty to work with.

It has 10 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
4/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 7 days ago, so Threshold is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 97/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands.

Automated pattern scan on 2026-11-22. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

Threshold compared with similar skills

All 4 of these similar skills score higher than Threshold; compare them before choosing.

SkillScoreStarsUpdatedFormat
Threshold (this skill)by KareemmSayed84107d agoMCP Server
claude-memby thedotmack100119.0ktodayCLAUDE.md
Agent-Reachby Panniantong100114.0ktodayCLAUDE.md
Understand-Anythingby Egonex-AI10093.7ktodayCLAUDE.md
hyperframesby heygen-com10088.2ktodayCLAUDE.md

Frequently asked questions

How do I install Threshold?
Run claude mcp add KareemmSayed -- npx -y github:KareemmSayed/Threshold. The install tabs above show the steps for each supported agent.
Which AI agents does Threshold work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is Threshold safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. It is MIT-licensed and scores 97/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is Threshold still maintained?
The repository was last updated 7 days ago, so Threshold is actively maintained.
<div align="center">

Threshold: Garmin MCP Server

Your Garmin data, analyzed by Claude, ChatGPT and any AI assistant. An open-source Garmin MCP server on the official Garmin Personal API. It answers questions about your training, sleep, HRV and recovery, with numbers computed by code, not guessed by the model.

CI License: MIT Runs on Cloudflare Workers

Deploy to Cloudflare

Website · Quick start · Connect your AI · FAQ · Changelog

<img src="docs/og.png" alt="Threshold, a Garmin MCP server for Claude, ChatGPT and any AI assistant" width="720"> </div>

"Am I recovered enough for intervals today?" · "Is my HRV trending down?" · "Am I ramping up too fast?" · "How even were my 10 x 1000 m, and am I faster than last time?" · "What can I run for 10k?" · "What will my form be on race day if I taper?" · "Does late training hurt my sleep?"

Threshold is a self-hosted Model Context Protocol (MCP) server that connects Garmin Connect to AI assistants. It runs on your own free Cloudflare account and talks to Garmin's official Personal API with your own key. No password, no scraping, no third-party service in between. It works with Claude (web, desktop, iOS, Android), ChatGPT, Claude Code, Cursor, VS Code, Codex, Gemini CLI, Windsurf and any MCP client.

Why Threshold

Other Garmin MCP servers hand the model raw JSON and hope it does the math. Threshold does the math.

| | Typical Garmin MCP | Threshold | | --- | --- | --- | | Readiness, training load (CTL/ATL/TSB, ACWR), HRV baseline | model guesses from raw JSON | computed in code, rules shown | | Interval sessions | averaged into kilometre splits | rep by rep: time, pace, heart rate, rest, fade | | Race predictions, training paces, taper forecast | model guesses | computed from your best efforts and load | | Aerobic decoupling, cardiac drift, best efforts, power curve | no | from the original FIT file | | VO2 max and performance condition hidden from the API | no | decoded from the FIT file | | Watches and accounts without HRV | no recovery signal | overnight stress and breathing rate on a baseline | | Full-history archive with SQL | no | D1 archive, read-only SQL tool | | Works on your phone (Claude / ChatGPT mobile) | rarely | OAuth built in | | Hosting | your laptop must stay on | Cloudflare free tier, one click | | Context-window friendly | 100 fields per item | compact, unit-labelled output | | Privacy | GPS and names in every response | GPS and identifiers removed by default |

What you can ask

| Tool | Answers | | --- | --- | | daily_briefing | "How am I today?" HRV, resting HR, sleep, overnight stress, sleep breathing rate, Body Battery, form and load ramp against your 60-day baselines, with a green / amber / red call and the rule behind it. Works without HRV, says when last night has not synced yet, watches for the pattern of an illness, and counts down to your next race. | | recovery_analysis | HRV on a personal baseline (ln of Garmin's overnight HRV average, 7-day rolling mean, normal band = baseline ± 0.5 SD), resting-HR drift, overnight stress and sleep breathing rate, sleep versus usual with sleep debt and bedtime regularity, and an illness watch. Shows how many of the last 7 nights have HRV. | | training_load | Fitness (CTL), fatigue (ATL), form (TSB), acute:chronic ratio, monotony, strain, weekly load, load by sport. | | training_status | "Is my training working?" Productive, maintaining, peaking, recovery, unproductive, overreaching or detraining, from load and the VO2 max trend. Plus load focus: how the last four weeks split between low aerobic, high aerobic and anaerobic work, and what is short. | | weekly_report | Week-by-week volume, load, session types, intensity split (80/20?), records set that week, sleep, HRV, resting HR, and change versus last week. | | metric_trend | Any metric over time (HRV, resting HR, sleep, bedtime, weight, VO2 max, running pace, efficiency, stride length...), slope, min/max, and comparison with the previous period. | | analyze_activity | One workout from its FIT file. An interval session comes back as reps (structure such as 10 x 1000 m, each rep's time, pace and heart rate, the rests, fade and consistency) instead of kilometre splits. Also HR zones, best efforts with all-time and 12-month records flagged, decoupling and drift on steady efforts (grade-adjusted on hilly runs), running form, strength sets, NP/IF/TSS, hidden VO2 max. | | compare_workouts | "Am I faster than last time?" One workout against earlier sessions of the same kind: the same reps, or steady efforts of the same length. Pace, heart rate and speed per heartbeat, with the trend. | | personal_records | Fastest 200 m to marathon (with the track distances 800 m, 1500 m and 3 km), 10–100 km rides, swim bests, power curve 5 s–60 min, heart-rate peaks, longest and hilliest sessions. | | race_predictor | "What can I run for 10k?" Race times from 1500 m to the marathon with a range and confidence, training paces (easy, marathon, threshold, interval, repetition) and critical speed, from your recent best efforts. For cycling: FTP estimate, critical power, W' and power zones. | | load_forecast | "What will my form be on race day?" Fitness, fatigue and form projected to a date if you train as usual, taper or rest, with your own planned days on top, and the load that lands on a target form. | | correlate | "Does late training hurt my sleep?" How two daily metrics move together, with a lag, a confidence interval and the sample size. | | race_calendar | Your target races, kept in your own archive. The briefing counts down to the next one, the predictor shows the gap to its goal, and the forecast aims at its date. | | list_activities | Activities by date, sport, type, session type or name, one compact line each. | | query_archive | Read-only SQL over your whole history, for everything else. | | get_health_data, get_day_detail, get_activity, get_profile | Garmin's own records, compacted: sleep stages, HRV readings, heart rate, SpO2, stress, Body Battery, weight, hydration, nutrition, menstrual cycle, fitness age. get_profile also checks your max and threshold HR settings against the heart rates in your activity files. | | sync_now, server_status, garmin_api_get | Pull fresh data now, health checks and archive coverage, and raw access to any Personal API path. | | show_view | Shows the answer as a card in this project's design, inside the chat in apps that support MCP Apps (Claude, ChatGPT, VS Code, Goose) and as a private link everywhere else. Presets build the card from the analysis tools, so the server supplies every number; custom blocks cover any other question. |

Clients that support MCP prompts also get morning check-in, weekly review, analyze last workout, workout progress and race readiness.

Quick start (5 minutes)

You need a free Cloudflare account and a Garmin watch that syncs to Garmin Connect.

1. Get your Garmin key. Open Garmin Connect → Personal API, click Create, and copy the key. Garmin shows it only once.

2. Deploy. Click the button, sign in to Cloudflare, and finish the deploy.

Deploy to Cloudflare

3. Add your two keys. In Cloudflare open Workers & Pages → threshold → Settings → Variables and secrets → Add variable. Add each one with type Secret, then click Deploy:

| Name | Value | | --- | --- | | GARMIN_API_KEY | the key from step 1 | | ACCESS_KEY | a password you make up, 20+ characters. You type it once per app you connect. |

4. Open your server. Cloudflare shows its address when the deploy finishes: https://threshold.<you>.workers.dev. The page says Ready and shows your MCP URL. If a key is missing, the page tells you exactly where to add it (and suggests a strong access key).

5. Connect Claude. Settings → Connectors → Add custom connector → paste the MCP URL → enter your access key. Other apps are below.

Your history fills in by itself in the background.

<details> <summary>Add or change a key later</summary>

Cloudflare dashboard → Workers & Pages → threshold → Settings → Variables and secrets → Add. Choose type Secret, enter the name (GARMIN_API_KEY or ACCESS_KEY) and the value, then Deploy.

</details> <details> <summary>Deploy from the command line instead</summary>
git clone https://github.com/KareemmSayed/Threshold.git && cd Threshold
npm ci
npx wrangler deploy                      # creates the database and KV store on first deploy
npx wrangler secret put GARMIN_API_KEY   # paste your Garmin key
npx wrangler secret put ACCESS_KEY       # paste your access key
</details>

Connect your AI

Your MCP URL is https://threshold.<your-subdomain>.workers.dev/mcp. Apps with a connector screen sign in with OAuth: they open your server's page, you type your access key, done. Apps with a config file send the access key as a bearer token.

<details open> <summary><b>Claude</b> (web, desktop, iOS, Android)</summary>

Settings → Connectors → Add custom connector → paste the MCP URL → Connect, then enter your access key on the page that opens. Add it once on claude.ai and it is on your phone too.

</details> <details> <summary><b>ChatGPT</b></summary>

Settings → Apps & Connectors → Advanced → turn on Developer mode. Then Create a connector, paste the MCP URL, choose OAuth, and enter your access key when asked.

</details> <details> <summary><b>Claude Code</b></summary>
claude mcp add --transport http threshold https://threshold.<you>.workers.dev/mcp \
  --header "Authorization: Bearer <ACCESS_KEY>"
</details> <details> <summary><b>Cursor</b> (<code>~/.cursor/mcp.json</code>), <b>Windsurf</b> (<code>~/.codeium/windsurf/mcp_config.json</code>)</summary>
{
  "mcpServers": {
    "threshold": {
      "url": "https://threshold.<you>.workers.dev/mcp",
      "headers": { "Authorization": "Bearer <ACCESS_KEY>" }
    }
  }
}

Windsurf names the field serverUrl instead of url.

</details> <details> <summary><b>VS Code</b> (<code>.vscode/mcp.json</code>)</summary>
{
  "servers": {
    "threshold": {
      "type": "http",
      "url": "https://threshold.<you>.workers.dev/mcp",
      "headers": { "Authorization": "Bearer ${input:threshold-key}" }
    }
  },
  "inputs": [{ "id": "threshold-key", "type": "promptString", "description": "Threshold access key", "password": true }]
}
</details> <details> <summary><b>Codex CLI</b> (<code>~/.codex/config.toml</code>)</summary>
[mcp_servers.threshold]
url = "https://threshold.<you>.workers.dev/mcp"
bearer_token_env_var = "THRE…[redacted]"
</details> <details> <summary><b>Gemini CLI</b> (<code>~/.gemini/settings.json</code>)</summary>
{
  "mcpServers": {
    "threshold": {
      "httpUrl": "https://threshold.<you>.workers.dev/mcp",
      "headers": { "Authorization": "Bearer <ACCESS_KEY>" }
    }
  }
}

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars10
CategoryAI
Updated7d ago
Forks11

Languages

TypeScript

Trust signals

97/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 info