Pelaris

Connect Pelaris to any MCP-compatible AI assistant for personalised fitness coaching. Plan training programs, log workouts, track benchmarks, manage goals, and get data-driven coaching insights.

GitHub

Pelaris MCP Server

AI fitness coaching through any MCP-compatible AI assistant. Plan training, log workouts, track benchmarks, manage goals, and get coaching insights — all through natural conversation.

Website · Integrations Guide · How It Works · Methodology

Connect

MCP Server URL: https://api.pelaris.io/mcp

ChatGPT

Settings → Apps → Add → enter the MCP Server URL above

Claude

Settings → Connectors → Add Custom → enter the MCP Server URL above → Advanced Settings → Client ID: pelaris-claude

Any MCP Client

Connect to https://api.pelaris.io/mcp — supports OAuth 2.0 with PKCE and Dynamic Client Registration.

Tools (21)

Read Tools (9)

ToolDescription
get_training_overviewView your training context, active programs, and recent sessions
get_active_programView current program with phase, weekly structure, and session details
get_session_detailsView a specific session's exercises, sets, targets, and feedback
get_benchmarksView benchmark values, progress history, and trends
get_body_analysisView body composition data and measurement trends
search_training_resourcesSearch curated training articles and resources
get_coach_insightGet data-driven coaching insights based on your training
get_onboarding_statusCheck profile setup completion status
get_weekly_debriefView weekly training summary and coaching focus

Write Tools (12)

ToolDescription
create_planned_sessionCreate a planned workout with exercises and targets
log_workoutLog a completed workout or mark a planned session as done
swap_exerciseGet alternative exercise suggestions
modify_training_sessionAdjust session volume, intensity, or schedule
record_injuryRecord an injury with body part, severity, and notes
update_profileUpdate equipment, availability, and preferences
send_feedbackSubmit coaching quality feedback
generate_weekly_planGenerate a new training plan
record_benchmarkRecord a benchmark value with history tracking
daily_check_inLog daily readiness, soreness, and sleep quality
manage_goalsCreate, update, complete, or list training goals
manage_programView, archive, or manage training programs

Authentication

OAuth 2.0 with PKCE. The server supports:

  • Pre-registered clients for ChatGPT and Claude
  • Dynamic Client Registration for all other MCP clients

Sports Supported

Strength · Running · Swimming · Cycling · Triathlon · CrossFit · General Fitness

Pelaris implements 28 science-based training methodologies. Learn more about our methodology.

Privacy

  • Pseudonymous user IDs (Firebase UIDs are never exposed)
  • PII scrubbing on all responses
  • Granular OAuth scopes
  • Users can disconnect anytime

Privacy Policy · Terms of Service

Built by

Bradley Hunt · About Pelaris

Related Servers