Alpha Progression MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Alpha Progression MCP Am I doing enough weekly sets for each muscle?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Alpha Progression MCP
Connect Claude (or any MCP client) to your Alpha Progression gym data: analyse your training and adjust your plan.
"Am I doing enough sets per week for each muscle?"
"Which lifts have stalled in the last 3 months?"
"Add a hamstring exercise to Day 2 and lower bench to 4 × 6."
Unofficial, not affiliated with Alpha Progression. Use it only with your own account.
Setup
Requires uv.
Log in once. Your email and password are not saved, only an access token (
~/.config/alpha-progression-mcp/token.json):uvx alpha-progression-mcp loginAdd it to Claude Code:
claude mcp add alpha-progression -- uvx alpha-progression-mcpOther clients:
{ "mcpServers": { "alpha-progression": { "command": "uvx", "args": ["alpha-progression-mcp"] } } }Restart your client.
Related MCP server: Workout Planner Ai MCP
Tools
Tool | Returns |
| Sets and training days per muscle, per week |
| Lifts improving or stalled, by muscle group (e1RM) |
| Recent workouts / every set of one workout |
| One exercise over time |
| Exercises by name or muscle |
| Your current plan with set and rep targets |
| Bodyweight and other measurements |
| Any single record |
| Change one thing in your plan |
Plan editing makes one targeted change per call, previews it first and only saves after you approve. Workout history is never touched; a backup of the plan is saved to ~/.config/alpha-progression-mcp/backups/ before each change, and it only changes what the free version of the app can (no RIR targets, deloads or periodisation). Changes appear in the app after it syncs. To turn editing off, set ALPHA_PROGRESSION_READ_ONLY=1.
Names can be partial ("bench press", "day 2"); unclear ones return suggestions.
Metrics: working sets exclude warm-ups (lighter sets before the first heavy set) and stretches. Sets per muscle count 1 for the target muscle and 0.5 for its main secondary muscles (fractional counting, Pelland et al. 2024). e1RM uses Epley, weight × (1 + reps / 30), up to 15 reps.
Troubleshooting
"Not logged in" / "login has expired": run the login command again.
"Too many login attempts": wait a few minutes; Alpha Progression locks login after wrong passwords.
Check the connection:
uvx alpha-progression-mcp statusLog out: delete
~/.config/alpha-progression-mcp/token.json.
Development
uv sync && uv run pytest && uv run ruff check . && uv run ruff format .The sync protocol is described in docs/api.md. MIT license.
Available Tools
13 toolsadd_plan_exerciseA
Add one exercise to a day of the training plan, at the end or right after the exercise named in after.
Example: day="Day 2", exercise="Seated Leg Curls (machine)", sets=3, reps=10, after="Deadlifts". Returns a preview; nothing is saved unless apply=true (only after the user approved the preview).
Inputs: day (required), reps (required), sets (required), exercise (required), +3 more.
find_exercisesARead-onlyIdempotent
Search exercises by name and/or muscle or group (e.g. "chest", "quads", "legs"), most recently done first.
By default only exercises the user has done, with how often and when last.
Inputs: query, muscle, only_used. Returns: result
get_documentBRead-onlyIdempotent
Any single stored document by id, for anything the other tools don't cover (e.g. "settings", "profile").
Inputs: doc_id (required).
get_exercise_historyARead-onlyIdempotent
One exercise over time: a summary plus one row per workout (newest first) with the top set,
e1RM, working sets and volume. exercise is a name (partial names like "bench press" work if they are
unambiguous) or an id. include_sets=true adds every set, including warm-ups.
Inputs: exercise (required), limit, end_date, start_date, +1 more.
get_measurementsARead-onlyIdempotent
Recorded body measurements (bodyweight, body fat, waist, ...) with dates, oldest first.
Inputs: no named parameters. Returns: result
get_plansARead-onlyIdempotent
Training plans: per day the exercises with their muscle and weekly set/rep/RIR targets. Only the current plan by default; active_only=false returns all plans.
Inputs: active_only. Returns: result
get_progressARead-onlyIdempotent
Which exercises are improving or stalled. Defaults to the last 6 months.
Per exercise done at least min_sessions times: sessions, working sets per week, e1RM at the start and
end of the range (median of the first and last 3 sessions, to smooth out single days), best e1RM,
change in % and the last date. Unweighted exercises compare top-set reps instead.
Sorted by muscle group. Filter with muscle or a group (chest, back, shoulders, arms, legs, core).
Inputs: muscle, end_date, start_date, min_sessions. Returns: result
get_sessionBRead-onlyIdempotent
One workout with every set: weight, unit, reps, RIR (reps in reserve), duration, notes and targets.
Inputs: session_id (required).
get_sessionsARead-onlyIdempotent
Performed workouts as compact summaries, newest first.
Per workout: name, plan, start, duration, working sets, volume (kg x reps), and per exercise the muscle,
working sets, top set and e1RM. skipped lists exercises that were planned but not done; mobility
lists stretches (not counted as training). Dates are YYYY-MM-DD, inclusive. Cached 5 min; refresh=true reloads.
Inputs: limit, refresh, end_date, start_date. Returns: result
get_weekly_trainingARead-onlyIdempotent
Weekly training load, the main input for volume and frequency guidance. Defaults to the last 8 weeks.
Per week (Monday start): workouts, minutes, working sets, and per muscle the fractional working sets
(1 per set for the target muscle, 0.5 for its main secondary muscles) and frequency (days trained).
average_per_week gives the same per muscle averaged over the range, with its muscle group. Weeks without
any workout (holiday, illness) are left out of the average unless skip_empty_weeks=false.
Filter with muscle (e.g. "chest") or a group: chest, back, shoulders, arms, legs, core.
Inputs: muscle, end_date, start_date, skip_empty_weeks.
remove_plan_exerciseA
Take one exercise off a day of the training plan. Past workouts with it stay in the history.
Example: day="Day 2", exercise="Overhead Triceps Extensions". Returns a preview; nothing is saved unless apply=true (only after the user approved the preview).
Inputs: day (required), exercise (required), plan, apply.
set_plan_targetsA
Change the target sets and/or reps of one exercise in the training plan.
Example: day="Day 1", exercise="Bench Press", sets=4, reps=6. day is a day name or number.
Returns a preview; nothing is saved unless apply=true (only after the user approved the preview).
Inputs: day (required), exercise (required), plan, reps, +2 more.
swap_plan_exerciseA
Replace one exercise on a day of the training plan with another, keeping its targets unless sets/reps are given.
Example: day="Day 2", exercise="Overhead Triceps Extensions", new_exercise="Dips", sets=3, reps=8. Returns a preview; nothing is saved unless apply=true (only after the user approved the preview).
Inputs: day (required), exercise (required), new_exercise (required), plan, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
Most tools target clearly distinct views: session summaries, single-session detail, plans, weekly load, progress trends, per-exercise history, exercise search, measurements. The main friction is the get_sessions/get_session pair and get_progress vs get_exercise_history, which require reading descriptions to separate (aggregate trend vs one exercise's rows), but the descriptions do make the boundary clear. get_document is a deliberate catch-all and is framed as a fallback, so it doesn't badly muddy selection.
All names are snake_case verb_noun with a small, predictable verb set (get_/find_/set_/add_/swap_/remove_), and mutating plan tools share a clean add/swap/remove/set family. Minor deviations: singular/plural get_session vs get_sessions is the only noun-form irregularity, and find_exercises breaks the get_ prefix for a read operation. Overall readable and predictable.
13 tools is squarely in the well-scoped range, split between 9 read/analysis tools and 4 plan-mutation tools. Each tool maps to a distinct question an agent would ask (how much did I train, is this lift stalling, what's on the plan) with no filler. The four plan-edit tools are arguably granular but each covers a real edit operation.
Read coverage of the training domain is strong (sessions, sets, plans, weekly volume, progress, history, measurements, arbitrary documents), and plan editing covers add/swap/remove/retarget. However the write surface is thin: there is no way to log a workout, record a body measurement, or create/rename a training plan, so an agent asked to capture new data hits a dead end. The preview/apply gating is good but doesn't fill those gaps.
Maintenance
Related MCP Connectors
Fitness MCP for coaches and gyms: build workouts and read clients' training from live Superset data.
Talk to your own gym log. Reps: Gym Workout Log (repsworkout.com) is a workout log for iPhone and Android. Connect it to Claude, ChatGPT or any MCP client to read your workout history, PRs, lift progression, weekly summaries, routines and training plan, and to save routines and plans after you confirm them. It never logs a workout for you and can’t delete your history. Sign in with an e-mail code, Apple or Google; new users can create a free account while connecting, then get the app to log workouts.
Connect Claude, Cursor or any MCP client to your GymUp training data.
Your strength-training data for any AI assistant: workouts, progress, muscle volume, routines.
Related MCP Servers
- FlicenseAqualityDmaintenancePersonal workout coach MCP server that logs exercises in natural language, tracks progress with SQLite, and provides coaching signals like estimated 1RM and volume trends.6-
- AlicenseNot gradedqualityCmaintenanceEnables creating workout plans, tracking progress, suggesting exercises, and calculating training volume through natural language, compliant with MCP protocol.MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to connect to a privacy-first, self-hostable workout planning and training log, allowing coaching agents to preview and apply program changes while accessing training data through OAuth-protected endpoints.AGPL 3.0
- AlicenseBqualityBmaintenanceEnables MCP clients to read account status, plans, and recent workouts, search official exercise names, and, when writes are enabled, apply confirmed preview-first plan changes and historical workout logs.22MIT