Skip to main content
Glama
seselcuk
by seselcuk

Coach MCP — Experiment / Lernprojekt

Dies ist keine Produktion. Es ist ein Nebenprojekt, das erstellt wurde, um die MCP-Version (Model Context Protocol) der Haupt-Coach-Anwendung zu erproben. Ziel: Die MCP-Architektur zu lernen und zu zeigen, wie sie aussehen würde, wenn sie in das Hauptprojekt integriert wäre.

Architektur

mcp_servers/data/demo.db  (SQLite — uydurma seed veri)
        ↑                    ↑
   MCP server'lar        Streamlit
   (Claude Desktop)      (localhost:8501)

Schlüsselidee: Eine Datenquelle, zwei verschiedene Clients — einer gesprächsbasiert (Claude Desktop + MCP), einer visuell (Streamlit).

Related MCP server: fitness-mcp-server

Unterschied zum Hauptprojekt

Hauptprojekt (Produktion)

Dieses Experiment

Modellzugriff

Push-Modell — Worker fügt Kontext an Prompt an

Pull-Modell — Claude zieht von MCP-Servern

Client

iOS + Streamlit

Claude Desktop + Streamlit

Deploy

Cloudflare Workers + D1

Lokales Python

Datenquelle

Echte Garmin-API

Erfundener SQLite-Seed

Zweck

Nutzer Mehrwert bieten

Architektur lernen/zeigen

MCP-Server

  1. garmin — Aktivitätsverlauf, Wellness, HR-Zonenverteilung, wöchentliche Belastung (aus SQLite)

  2. pain — Schmerzverlauf + neues Schmerzloggen (INSERT in SQLite)

  3. coach-rulescoach-principles.md + pain-rubric.md als Prompt-Vorlage

Details und API unter: mcp_servers/README.md

Schnellstart

# 1. Bağımlılıklar
python3.11 -m venv .venv
.venv/bin/pip install -r requirements.txt

# 2. DB seed
.venv/bin/python -m mcp_servers.data.seed

# 3. Claude Desktop config kur
cp mcp_servers/claude_desktop_config.example.json \
   "$HOME/Library/Application Support/Claude/claude_desktop_config.json"

# 4. Claude Desktop'ı restart (Cmd+Q sonra yeniden aç)

# 5. Streamlit dashboard (opsiyonel, görsel demo için — port 8502, ana projenin 8501 ile çakışmaz)
.venv/bin/streamlit run streamlit_demo/app.py --server.port 8502

Demo-Szenario

3 Szenarien und Ablauf für die Präsentation unter: DEMO.md

Ordnerstruktur

antrenör_mcp/
├── mcp_servers/
│   ├── garmin/server.py       Aktivite + wellness + zone MCP
│   ├── pain/server.py         Ağrı geçmişi + log_pain tool
│   ├── coach_rules/server.py  Prensipler + rubric prompt template
│   ├── data/seed.py           DB seed script
│   ├── data/demo.db           SQLite (git'e girmez)
│   └── claude_desktop_config.example.json
├── streamlit_demo/app.py      3 tab dashboard
├── docs/
│   ├── coach-principles.md    Zone 2, shin, deload kuralları
│   └── pain-rubric.md         0-10 ağrı ölçeği
├── DEMO.md                    Sunum senaryosu
└── requirements.txt
A
license - permissive license
-
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    A
    quality
    A
    maintenance
    Enables Claude to access and query your Garmin Connect data, including sleep, activities, training load, and health metrics, through a set of read-only MCP tools.
    18
    1
    MIT
  • F
    license
    -
    quality
    D
    maintenance
    Provides MCP servers for Claude to access fitness data from Strava and intervals.icu, enabling natural language queries for activity analysis, advanced training metrics, and wellness tracking.
    1
  • F
    license
    -
    quality
    C
    maintenance
    Enables workout tracking and coaching within Claude conversations, managing exercise configs, logs, streaks, and health metrics via an MCP server with PostgreSQL.

View all related MCP servers

Related MCP Connectors

  • Garmin data in Claude & ChatGPT via the Garmin Health API. OAuth sign-in, no password sharing.

  • Garmin data in Claude: 135 tools — activities, sleep, HRV, training, workouts. Free, open source.

  • WHOOP recovery, strain, sleep and workouts in Claude via official WHOOP OAuth. Free, open source.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/seselcuk/antrenor-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server