A stateless MCP server providing evidence-based strength training tools that encode classical powerlifting programs, fatigue modeling, and training science principles — with all state managed by the calling agent.
Browse training programs (list_training_templates): Explore a built-in library of classical programs (5/3/1, Texas Method, Madcow, GZCLP, nSuns CAP3, Coan-Philippi, Smolov Jr), filterable by category (powerlifting, strength, peaking) and difficulty (beginner, intermediate, advanced).
Retrieve weekly training plans (get_template_plan): Get a specific week's prescribed sessions from any template, including exercises, sets, reps, intensity, and AMRAP flags.
Look up exercise form guidance (lookup_exercise_form): Get form cues, common mistakes, and equipment-filtered alternatives for any exercise.
Learn training science principles (explain_principle): Get cited explanations of concepts like RPE autoregulation, periodization, the Banister model, deload triggers, and volume landmarks.
Calculate fatigue scores (calculate_fatigue_score): Compute Banister fitness-fatigue metrics (CTL/ATL/TSB) from recent training history, optionally incorporating recovery data like sleep and soreness.
Get session modification suggestions (suggest_session_modification): Receive actionable adjustment recommendations (scale weight, change intensity, deload, etc.) based on planned vs. actual performance and current fatigue state.
Apply plan adjustments (apply_plan_adjustment): Modify a week's plan by applying adjustments such as DELOAD_WEEK, SCALE_WEEK, SHIFT_VOLUME, or ADD_REST_DAY, returning the adjusted plan JSON.
Get today's session recommendation (recommend_session_for_today): Receive a personalized session recommendation with rationale based on your template, current week, fatigue state, and last session.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@strength-training-mcp Recommend today's session with fatigue score -15."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A stateless MCP server exposing 8 tools for evidence-based strength training. Encodes classical powerlifting programs (5/3/1, Texas Method, Madcow, GZCLP, nSuns CAP3, Coan-Philippi, Smolov Jr), the Banister fitness-fatigue model, RPE-based autoregulation, and an adjustment policy engine.
No user data is stored on the server. All state lives in the calling agent. The server is a pure function: same inputs → same outputs.
Transport | Support | Entry Point | Use Case |
Stdio | ✅ |
| Claude Desktop, Claude Code, Cursor |
Streamable HTTP | ✅ |
| ModelScope, Aura, remote agents |
SSE | ❌ | — | Not implemented (use Streamable HTTP instead) |
Related MCP server: RepStack
uvx --from strength-training-mcp strength-training-mcpuvx --from strength-training-mcp strength-training-mcp-http --port 8080Test:
curl http://localhost:8080/health
# → {"status":"ok","version":"0.1.1"}For MCP calls over HTTP, use any MCP client (e.g., fastmcp.Client, Claude Desktop, or ModelScope) pointing at http://localhost:8080/mcp.
This package is published to PyPI as strength-training-mcp. ModelScope can deploy it directly via uvx.
In ModelScope MCP deployment console, select Stdio or Streamable HTTP.
Recommendation: Use Stdio for the simplest one-click deployment.
{
"mcpServers": {
"strength-training": {
"command": "uvx",
"args": [
"--from",
"strength-training-mcp",
"strength-training-mcp"
],
"env": {}
}
}
}Deploy the HTTP server first (see Self-Host below), then fill your public URL:
{
"mcpServers": {
"strength-training": {
"type": "http",
"url": "https://your-domain.com/mcp"
}
}
}This server requires no API keys, no environment variables, and no database. Leave parameter config empty.
After deployment, test:
curl https://your-deployment-url/health
# → {"status":"ok","version":"0.1.1"}See docs/selfhost.md for:
systemd service setup
nginx reverse proxy (hide application port)
Caddy + HTTPS
Docker deployment
Minimal production setup:
# Install
uv tool install strength-training-mcp
# Run behind nginx on port 80
strength-training-mcp-http --host 127.0.0.1 --port 3492Then configure nginx to proxy 80 → 127.0.0.1:3492.
Tool | Purpose |
| Browse the built-in program library |
| Get a specific week's prescribed sessions |
| Get form cues + alternatives for an exercise |
| Explain a training science principle with citation |
| Compute Banister CTL/ATL/TSB from training history |
| Get adjustment recommendations based on fatigue + actual |
| Apply aggregate adjustments to a week (deload, etc.) |
| Compose today's session with rationale |
See docs/api.md for full tool reference, input schemas, and error codes.
{
"mcpServers": {
"strength-training": {
"command": "uvx",
"args": [
"--from",
"strength-training-mcp",
"strength-training-mcp"
]
}
}
}uv sync --all-extras
uv run pytest tests/unit # unit tests
uv run pytest tests/integration # E2E tests
uv run pytest --cov=src/strength_training_mcpAll templates and principles cite their original public sources. See docs/rts-principles.md for citations.
MIT
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for Withings health data — sleep, activity, heart, and body metrics.
Wger MCP — wraps wger Workout Manager REST API (free, no auth for read)
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/daiduo2/strength-training-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server