Strength Training MCP Server

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.

Installation

# Install uv (one-time)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Install deps + create venv
uv sync --all-extras

Running

# HTTP server
uv run python -m strength_training_mcp.server

# stdio server (Claude Desktop / Claude Code)
uv run strength-training-mcp

HTTP server starts on http://0.0.0.0:8080

• MCP JSON-RPC endpoint at POST /mcp
• Health check at GET /health

Deployment

• ModelScope: see modelscope-deploy.md — deploy via uvx.
• Your own cloud server / VPS: see docs/selfhost.md for systemd + Caddy setup.

Quick start on any machine:

# HTTP server (for self-host / remote clients)
uvx --from strength-training-mcp strength-training-mcp-http --port 8080

# stdio server (for Claude Desktop / Claude Code local)
uvx --from strength-training-mcp strength-training-mcp

Agent Integration

See docs/agent-integration/ for setup guides:

• Claude Desktop
• Aura
• Cursor
• Custom Agent (Python SDK)

Tools

Tool	Purpose
list_training_templates	Browse the built-in program library
get_template_plan	Get a specific week's prescribed sessions
lookup_exercise_form	Get form cues + alternatives for an exercise
explain_principle	Explain a training science principle with citation
calculate_fatigue_score	Compute Banister CTL/ATL/TSB from training history
suggest_session_modification	Get adjustment recommendations based on fatigue + actual
apply_plan_adjustment	Apply aggregate adjustments to a week (deload, etc.)
recommend_session_for_today	Compose today's session with rationale

See docs/api.md for full tool reference.

Development

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_mcp

Knowledge Sources

All templates and principles cite their original public sources. See docs/rts-principles.md for citations.

License

MIT (subject to ModelScope deployment terms).