Connects to Supabase as the backend database for storing and retrieving habit tracking data, including logging habits, retrieving daily status, streaks, and mission overview.
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., "@Zenith MCP Server log my cold shower habit for today"
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.
A personal habit tracking MCP server built for an AuDHD + PDA brain.
Tracks the 6 daily non-negotiables of a 90-day mission — connected to Supabase. No UI. No friction. Just a tool your AI can call.
Tool | What it does |
| Log a habit as done today |
| Full dashboard of today's habits |
| Consecutive day streak for any habit |
| Full 90-day progress stats |
Related MCP server: notion-mcp
prayer_before_phone
cold_shower
box_breathing
pullup_gtg (multi-session, tracks reps)
a25_block
video_published
No negative habit tracking. Pink Elephant rule enforced.
# 1. Clone and install
git clone https://github.com/YOUR_USERNAME/zenith-mcp
cd zenith-mcp
uv sync
# 2. Add your credentials
cp .env.example .env
# Edit .env with your Supabase URL and secret key
# 3. Run the DB migration in Supabase SQL Editor
# (paste contents of setup_db.sql)
# 4. Run the server
uv run server.pyBuilt in public. AuDHD developer. Varna, Bulgaria.
Returns a full 90-day mission progress overview:
How many days have passed and remain
Which habits have the highest and lowest completion rates
Total pull-up GtG reps logged across the mission
Inputs: no named parameters. Returns: object
Returns the current consecutive-day streak for a specific habit.
Inputs: habit_name (required). Returns: object
Returns a full dashboard of which habits are done/not done today, today's pull-up GtG total reps, and mission day progress.
Inputs: no named parameters. Returns: object
Mark a habit as completed for today.
Inputs: habit_name (required), pullup_reps. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool serves a clearly distinct purpose: logging a completion, viewing today's dashboard, checking a specific habit's streak, and viewing overall mission progress. There is no overlap or ambiguity between them.
All tool names follow a consistent verb_noun pattern: log_habit, get_today_status, get_streak, get_mission_overview. The verbs are consistent ('log' and 'get'), and the nouns clearly describe the target.
With 4 tools, the set is concise and well-scoped for a habit-tracking mission server. Each tool covers a necessary interaction (log and three read views), and the count is within the ideal range.
The server covers core logging and status views, but lacks a way to list available habits or manage them (create/update/delete). An agent cannot discover valid habit names, which could cause failures when calling log_habit or get_streak.
MCP server for interacting with the Supabase platform
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
The **OTTTA MCP server** lets you manage your habit trackers. Add / create / update / delete groups, trackers and values. The idea behind OTTTA is to make tracking very easy. The app is simple, you create groups, in the groups you put things to track on a daily basis and then it generates graphs. You can log values to the trackers via the [OTTTA website](https://ottta.com/), via our API, our MCP of course and via the OTTTA Chrome Extension. Soon more ways will be available.
Official Todoist MCP server. Manage tasks and projects. Hosted, no API key needed.
