Training and measurement trends
Review load, readiness, intensity, durability, sport-specific evidence, and body-weight history across the period you ask about.
MCP Server
Connect ChatGPT or Claude to your training data
Use the read-only Quantified Self MCP server to let ChatGPT, Claude, or another compatible client analyze your training, review your season, or plan your next workout using only the data categories you approve.
MCP serverChatGPTClaudeRead-onlyTrainingSleepActivitiesRoutes
Training Questions
Ask about training, workouts, sleep, measurements, and routes
Use the parts of your Quantified Self account you approve to investigate a training question, inspect a workout, or build a longer analysis in your preferred AI client.
Recorded Health metrics
Explore all-day heart rate, HRV, stress, Body Battery or resources, movement, energy and blood pressure with separate Health permission. Sources stay separate; Body Battery keeps its Garmin points scale. Bounded sample trends include UTC times. Body composition also needs Body measurements access. Reconnect an existing client to grant Health access.
Workout details and charts
Find recent activities, compare recorded metrics, and inspect workout summaries, laps, swim lengths, MTB jumps, and chart-ready data.
Sleep, readiness, and daily context
Review sleep duration, score, stages, HRV, sleeping heart rate, blood oxygen, respiration, readiness, and recent training trends when those signals are available.
Saved routes and optional locations
Find saved routes by sport, name, or recency. A separate location permission adds route geometry, nearby search, segment endpoints, and waypoints.
Access Boundaries
Read-only by design, with separate permissions
Choose which data categories an external client can read, then review or disconnect it from Connections at any time.
Separate optional scopes
Approve training metrics, Health metrics, measurements, workout details, sleep, routes, Timeline notes, or locations separately. Activity locations and saved-route locations remain independent permissions.
No settings or data writes
MCP clients cannot create, edit, delete, or backfill Health measurements, activities, routes, sleep records, dashboard settings, or Training state. Revocation blocks future access.
Only the requested data is returned
Original files, full-resolution recordings, provider credentials, source keys, and unrequested streams are excluded. Exact coordinates require the matching location permission.
Location access stays separate
Activity and route locations are never implied by another permission. Place-name searches send only the location text to Mapbox for geocoding.
FAQ
MCP Server FAQ
What does the Quantified Self MCP server do?
It lets a compatible external AI client answer questions using the Quantified Self training metrics, body-weight history, workout details, sleep summaries, and saved routes you approve. Access remains read-only.
Can I use the MCP server with ChatGPT or Claude?
Yes. Add https://quantified-self.io/mcp as a custom MCP connection in a compatible ChatGPT or Claude client, sign in to Quantified Self, and approve the read-only permissions you want to grant. External clients have their own privacy and retention practices.
Can an MCP client read my Timeline notes?
Only with separate Timeline notes permission, which starts unchecked and requires reauthorization for existing clients. It includes full note titles and details, including notes hidden from charts, and may contain sensitive health or personal information. Revocation cannot erase copies already received. Notes cannot grant permission to change a Training plan.
Can an MCP client rearrange my dashboard or change my data?
No. The MCP server is read-only. It cannot write dashboard settings, activities, routes, Training state, or sleep records.
Does MCP access expose my original activity or route files?
No. An activity chart may selectively parse an existing original file in memory, but the file itself, full-resolution recording, absolute sample timestamps, unrequested streams, provider payloads, credentials, and storage paths are not returned or copied into another activity store.
Can an MCP client see exact locations?
Only if you separately approve Activity locations or Saved-route locations and geometry. Activity location covers starts, ends, MTB jumps, nearby activity search, and optional breadcrumbs. Route location covers bounds, previews, segment endpoints, nearby route search, and waypoints. Granting one never exposes the other.
Next Step
Choose what your AI client can use
Create an account, connect your training sources, and approve only the data categories needed for the questions you want to ask. Review or revoke the connection at any time.