AIm Workout Journal MCP server

AIm Workout Journal

A workout tracker your AI assistant writes to. AIm is an MCP server plus a mobile web app (PWA): you describe a session in Claude or ChatGPT in your own words, the assistant logs it through MCP, and the app shows the program, the history, records, estimated 1RM and per muscle load. The coaching prompts live on the server, so the assistant plans from your logged weights instead of generic advice.

Live at aim-journal.com. Free, and it runs inside the AI subscription you already pay for rather than being a second one. Guides: connect a workout tracker over MCP, AI personal trainer, 1RM calculator.

How it works

There are two ways in, on the same host, and both resolve to the same user_id:

https://<app>/mcp                OAuth 2.1 — add as a connector, approve in the browser
https://<app>/{token}            mobile web app / installable PWA
https://<app>/{token}/mcp        the original connector address, still supported
https://<app>/{token}/api/*      read only JSON the UI consumes

OAuth is what a connector uses now. The server is an OAuth 2.1 resource server: an unauthenticated call gets a 401 carrying RFC 9728 protected-resource metadata, the client discovers the authorization server from it, registers itself dynamically, and the user approves on a consent screen this app serves. Supabase Auth is the authorization server, so no authorization codes or access tokens are stored here; the access token's sub is mapped to an account through users.supabaseuserid. Nothing secret is pasted by hand.

The URL token predates it and still works, which is why every link already in someone's inbox kept working when OAuth landed. A token resolver middleware maps the leading path segment to a user and scopes every query by user_id; the OAuth path sets the same context variable from a verified token instead. Two doors, one scoping rule.

What the MCP server exposes

20 tools over stateless streamable HTTP (FastMCP):

(paste an export from another tracker or a photo of a notebook page).

• Logging: logsession, updatesession, updateset, deletesession, import_document

Epley), getprogram, getgoals, getbodymetrics.

• Reading: getsessions, getsession, get_stats (volume, progression, estimated 1RM via

listexercises, upsertexercise.

• Catalogue: searchexercisepool (a curated global pool with illustrations),

experience, equipment, injuries and recent loads together with the prompt for the task at hand (next workout, new program, weekly review), so the assistant plans from data rather than from nothing. reviewprogramdraft, updatecoachprofile, upsertgoal, logcoachevent, logbody_metric keep that context current.

• Coaching: getcoachingcontext is the important one. It returns this user's goal,

Repo layout

api/index.py      Vercel entrypoint (must stay at repo root, see below). Imports backend/src.
requirements.txt  Vercel's Python build reads this (must also stay at repo root).
backend/          Python package, tests, scripts, DB migrations.
web/              Vite + React SPA (own package.json, own dev server) and the static guide pages.

api/index.py and requirements.txt cannot move: Vercel's zero config Python builder only auto detects functions under a root level api/, and only installs a root level requirements.txt alongside them. Everything else in backend/ (pyproject.toml, uv.lock, tests, scripts, supabase/) is hidden from the Vercel build by .vercelignore, so Vercel treats the repo as a static SPA plus one Python function.

Shortened. The full README is on GitHub.