rawwatts-demo
Server Details
No sign-in: a real cyclist's indoor rides, read-only. Ask your AI about his power and heart rate.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
Tools are mostly distinct: list_rides vs get_ride vs get_ride_series separate list, summary, and time-series access. get_power_curve overlaps slightly with get_ride (which also returns a ride's power curve) and with training summaries, but the period-based purpose is clear enough.
All tools use a consistent snake_case verb_noun pattern: get_* for single-resource fetches and list_* for collections. No mixed conventions or vague verbs.
Seven tools is well-scoped for a cycling analytics demo, covering athlete, rides, ride detail, ride series, power curve, weekly summary, and workouts. Each tool has a clear role without redundancy.
The read surface is fairly complete for rides and athlete data, but list_workouts explicitly references save_workout's description while no save_workout tool is present. That creates a dead end for workout creation, and there are no update/delete operations for athlete or workouts.
Available Tools
7 toolsget_athleteBInspect
The rider's body settings (FTP, FTP history, max HR, weight, age in years, units), the dates of their first and last ride, the ride count and when the app last synced. ftp_history only holds FTPs a test replaced ("Use as FTP"); an FTP the rider typed in is not recorded there.
Inputs: no named parameters.
get_power_curveAInspect
Best average power per duration (5 s to 60 min) over a period, with the ride each best came from. Dates YYYY-MM-DD, inclusive; both optional (default: all rides).
Inputs: to_date, from_date.
get_rideBInspect
One ride's full summary as the app computed it: stats (incl. normalized power), laps, power curve, power zones, left/right balance, heart rate, DFA-alpha1 per minute (experimental), the workout ridden and the FTP used.
Inputs: id (required).
get_ride_seriesBInspect
A ride's second-by-second data averaged down to resolution_s (default 30; at most 720 points, so long rides get a coarser resolution). fields from: power, target, hr, cadence, right_pct, speed, distance, step. Default: power, hr, cadence. t_s is the start of each interval in recorded seconds.
Inputs: id (required), fields, resolution_s.
get_training_summaryAInspect
Per week (Monday-Sunday) for the last weeks weeks (default 8, max 104): rides, hours, kJ and seconds per power zone (Coggan 1-7, by each ride's FTP).
Inputs: weeks.
list_ridesAInspect
The rider's rides, newest first: id, local start, duration, kJ, average and max power, average and max heart rate, kind (free, ramp, rampLite, edge, workout). Dates are YYYY-MM-DD in the rider's local time, both inclusive. limit: 1-500, default 50. Ids follow the order the app synced the rides, not the ride dates.
Inputs: limit, to_date, from_date.
list_workoutsAInspect
Every workout set as text: the rider's own (read-only for you) and each assistant's, with who wrote it. The workout format is in save_workout's description.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Your own cycling data for your AI assistant: rides, power, climbs and routes. Read-only.
Your swim, bike and run training: readiness, HRV, sleep, workouts and race predictions. Read-only.
Ask your AI about your fitness: activities and data from Garmin, COROS, Strava, GPX and more
Smart trainer rides from the RawWatts iPhone app: power, heart rate, laps. Writes ERG workouts.
1
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI agents to query Matrix / Johnson Fitness ride history, exposing per-10-second power, cadence, resistance and heart-rate samples plus cross-ride views like power curves, training volume, and ride comparisons. Runs over a cached history downloaded without credentials, or signs in once to refresh it.777 npmMIT
- AlicenseAqualityDmaintenanceProvides AI assistants with read-only access to an athlete's Intervals.icu training data, including activities, wellness metrics, zones, and planned events, for use with MCP clients like ChatGPT and Claude.15MIT
- AlicenseNot gradedqualityBmaintenanceEnables a single owner to query their intervals.icu training data — athlete profile and recent activities — from ChatGPT through an OAuth-protected, read-only connection. It authenticates the owner via GitHub sign-in and exposes a read-only toolset with no write, delete, or coach capabilities.Apache 2.0
- AlicenseAqualityBmaintenanceEnables AI assistants to read and analyze athlete training data, including fitness summaries, activities, and profiles, to help plan training.369 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.