Pelaris

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 (29)

Read Tools (12)

Tool	Description
get_training_overview	View your training context, active programs, and recent sessions
get_active_program	View current program with phase, weekly structure, and session details
get_session_details	View a specific session's exercises, sets, targets, and feedback
resolve_exercise_ids	Resolve exercise names to canonical exercise IDs before planning or logging
get_benchmarks	View benchmark values, progress history, and trends
get_body_analysis	View body composition data and measurement trends
search_training_resources	Search curated training articles and resources
get_coach_insight	Get data-driven coaching insights based on your training
get_onboarding_status	Check profile setup completion status
get_weekly_debrief	View weekly training summary and coaching focus
get_program_status	Check the status and progress of your training programs (running, paused, replaced or removed)
list_goals	List your training goals with completion status and linked benchmarks

Write Tools (17)

Tool	Description
complete_intake	Complete onboarding intake and persist your training profile
generate_program	Get the link that starts your training program in Pelaris (programs are built in Pelaris)
create_planned_session	Create a planned workout with exercises and targets
log_workout	Log a completed workout or mark a planned session as done
log_completed_session	Log a full completed session with exercises, sets, and feedback
swap_exercise	Get alternative exercise suggestions
modify_training_session	Adjust session volume, intensity, or schedule
update_session	Update the details of an existing planned session
delete_session	Delete a single planned session
delete_sessions	Delete multiple planned sessions
record_injury	Record an injury with body part, severity, and notes
update_profile	Update equipment, availability, and preferences
send_feedback	Submit coaching quality feedback
record_benchmark	Record a benchmark value with history tracking
daily_check_in	Log daily readiness, soreness, and sleep quality
manage_goals	Create, update, or complete training goals
manage_program	Set a program aside: removes one you have not started, and points you to Pause, Stop and Remove in the app for the rest

Example prompts

Once connected, talk to your AI assistant naturally. It maps your intent to the tools above:

• "What does my training look like today?" → get_training_overview / get_active_program
• "Log my 5k run, felt easy, RPE 4." → log_workout
• "Create an upper body session for tomorrow." → create_planned_session
• "How are my benchmarks trending?" → get_benchmarks
• "Swap the barbell bench for a dumbbell variation." → swap_exercise
• "My right shoulder's been sore." → record_injury
• "I want a training program." → generate_program (returns your Pelaris link, where your program is built)

(Illustrative prompts only; no personal data is shown. Responses are grounded in your own training data and PII-scrubbed.)

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

Development

• npm run build, then npm test. Every test file is listed in scripts/run_tests.mjs, and Firestore points at a dead loopback port unless an emulator is set, so a test never reaches a real project. CI runs both before each deploy.
• Local runs use scripts/run_local_gateway.sh. It refuses to start unless Firestore, the OAuth function and the core bridge are all on loopback, the port is not an emulator port, and the secrets are the local test values.
• End to end, locally: with the Pelaris local stack up (emulators, functions and web, sends off), node tools/connector_e2e/run_connector_e2e.mjs --reseed --start-gateway --transcript <file> starts this gateway under wayfinder's egress guard and drives it with a real MCP client as seeded people (newcomer, program holder, unstarted, started and two-program athletes), then checks the replies, the emulator's data and the gateway log. Local only: it refuses anything that is not loopback and mints test tokens with the runner's published dummy secret. The header of the script lists the people and the flags.
• The contracts shared with the Pelaris backend live in test_fixtures/ (redirect policy, token ownership, return predicates). Each is pinned by its SHA-256 on both sides.

Built by

Bradley Hunt · About Pelaris