GoalTrack
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., "@GoalTrack I drank 500ml of water, log it and check my streak"
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.
GoalTrack — Generic Daily Goal Tracker (MCP Server)
The problem it solves: most daily-goal tracking apps are built for one metric — a water app, a step counter, a screen-time limiter — even though the underlying pattern is identical: log amounts throughout the day, check them against a target, and track whether you're keeping a streak. GoalTrack lets an LLM (Claude, or any MCP client) manage any number of goals at once — water, steps, pages read, screen time, calories, whatever — and get timezone-correct progress and streaks for each.
What it does
Tool | Purpose |
| Create a goal (name, unit, target, direction, threshold, timezone) |
| Update any field on an existing goal |
| Soft-delete (default, keeps history) or hard-delete a goal |
| List all goals with today's progress inline |
| Log an amount against a goal |
| Fix a mislogged entry's amount |
| Remove a logged entry |
| Today's total vs target for one goal, with % complete |
| Daily totals + met/missed status over the last N days |
| Current streak + longest streak for a goal |
Plus a goaltrack://goal-templates resource (a small library of common goal
presets an LLM can suggest — Water, Steps, Screen Time, etc.) and a
daily_encouragement_prompt prompt template that asks the assistant to
write a short, warm nudge about today's progress.
Direction: at_least vs at_most
Not every goal wants "more" — screen time and calorie limits want you to
stay under a number. Every goal has a direction:
at_least— met iftoday_total >= target * (threshold_pct / 100)(e.g. water: hit 90%+ of 2500ml)at_most— met iftoday_total <= target * (1 + (100 - threshold_pct) / 100)(e.g. screen time: stay within 10% over a 120min cap when threshold_pct=90)
threshold_pct always means "how strict is this" — it just bends in the
direction that matches the goal.
Related MCP server: helm-personal-os
The interesting engineering bit
Two things had to be designed carefully, same spirit as SubTrack's calendar-arithmetic problem:
What counts as "today"? Every logged entry computes and stores a
local_datefrom the goal's own IANA timezone at log time (compute_local_date()), not server time. If a goal's timezone is changed later, past entries keep their originallocal_date— history is never silently rewritten.Streaks.
compute_streaks()walks backward day-by-day from yesterday (today is deliberately excluded — an in-progress day should never break a streak just because it isn't finished yet) until it hits a day that didn't meet the goal, for the current streak. Longest streak is found by scanning every day from the goal's first-ever entry forward and tracking the longest run of met days.
Why the tools are async def
Every tool here is async def, and all SQLite access goes through
aiosqlite instead of the stdlib sqlite3, for the same reason as the
reference project this was modeled after:
FastMCP thread-offloads plain
deftools automatically, so a sync version wouldn't literally freeze under light load.But
async def+ a blocking driver inside it is worse than staying sync — FastMCP does not thread-offloadasync deftools, so a blocking DB call would stall every other concurrent request on the event loop.So: go
async defand use a genuinely async driver all the way down. This composes cleanly if more awaitable I/O (HTTP calls, etc.) gets added later, and doesn't burn a worker thread per in-flight DB call.The one exception:
goal_templates.jsonis read with plain sync I/O — it's a few hundred bytes, read rarely, not worth anaiofilesdependency.
Project structure
goaltrack-mcp/
├── server.py # the whole server — module-level `mcp` object
├── client_test.py # quick manual smoke-test client
├── pyproject.toml # project metadata + deps (managed by uv)
├── uv.lock # locked, reproducible dependency versions
├── .python-version # pins the Python version uv uses
├── .gitignore
└── README.mdgoal_templates.json and goaltrack.db are not committed —
server.py creates them automatically on first run (init_templates() /
init_db()). If you want a fixed template list to survive redeploys,
remove goal_templates.json from .gitignore and commit your edited copy.
Run it locally (uv)
No manual venv step needed — uv run creates and syncs .venv from
uv.lock automatically the first time you use it.
uv run server.py
# Starting MCP server 'GoalTrack' with transport 'http' on http://0.0.0.0:8000/mcpTest it with the included client:
uv run python client_test.pyIf you want to test with a stdio-based client (e.g. wiring this into
Claude Desktop for local use), run it via the FastMCP CLI, which overrides
the transport regardless of what's in __main__:
uv run fastmcp run server.py:mcp --transport stdioAdding or updating dependencies
Don't hand-edit pyproject.toml's dependency list — let uv manage it:
uv add some-package
uv add some-package --upgrade
uv lock --upgradeDeploy to FastMCP Cloud
Push this folder to a GitHub repo — commit
pyproject.tomlanduv.lock(don't commit.venv/).Sign in at fastmcp.cloud with GitHub and create a new project from the repo.
Set the entrypoint to
server.py:mcp.Deploy. You'll get a URL like
https://<project>.fastmcp.app/mcpthat any MCP client — including Claude, via a custom connector — can call.
A note on storage
This uses SQLite on local disk, which is not guaranteed to survive a
redeploy on most managed platforms. Once the tool logic feels solid, a good
next exercise is swapping sqlite3/aiosqlite for a hosted database
(Turso/libSQL, Postgres via asyncpg, Supabase) via os.getenv("DATABASE_URL").
Ideas to extend it
Add a
notify_if_at_risktool that checks all active goals late in the day and flags ones that are behind, usingdaily_encouragement_prompt(or a new nudge prompt) to draft the message.Add a
notescolumn onentriesfor context per log (e.g. "gym day").Add authentication (FastMCP supports bearer-token auth) and a
user_idcolumn once you're ready to make this a private, multi-user server.Add a
weekly_summarytool that aggregateshistory()output across all active goals into one digest.
Available Tools
10 toolsadd_goalAdd GoalC
Create a new daily goal to track.
direction: 'at_least' (hit at least the target, e.g. water/steps) or 'at_most' (stay at or under the target, e.g. screen time). threshold_pct: how strict 'met' is. For at_least, % of target required. For at_most, 100 = no slack, lower = more allowed slack. timezone_name: IANA tz string, e.g. 'Asia/Karachi', 'America/New_York'.
Inputs: name (required), unit (required), target_amount (required), direction, +2 more. Returns: object
delete_entryDelete EntryC
Remove a logged entry entirely.
Inputs: entry_id (required). Returns: object
delete_goalDelete GoalA
Remove a goal. By default soft-deletes (active=0, history kept). Pass hard_delete=True to permanently remove the goal AND its entries.
Inputs: goal_id (required), hard_delete. Returns: object
edit_entryEdit EntryC
Fix a mislogged entry's amount.
Inputs: amount (required), entry_id (required). Returns: object
edit_goalEdit GoalB
Update any field on an existing goal. Only provided fields change.
Inputs: goal_id (required), name, unit, direction, +3 more. Returns: object
get_progressGet ProgressB
Today's total vs target for one goal, with % complete.
Inputs: goal_id (required). Returns: object
historyHistoryB
Daily totals and met/not-met status for a goal over the last N days (including today, which is always shown as in-progress rather than met/failed).
Inputs: goal_id (required), days. Returns: result
list_goalsList GoalsB
List goals with today's progress inline for each.
Inputs: include_inactive. Returns: result
log_entryLog EntryB
Log an amount against a goal. logged_at is an ISO-8601 UTC datetime string (e.g. '2026-09-11T14:30:00Z'); defaults to now if omitted.
Inputs: amount (required), goal_id (required), logged_at. Returns: object
streak_statusStreak StatusB
Current and longest streak for a goal (streaks measured in days met).
Inputs: goal_id (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool targets a clearly distinct operation: goal CRUD, entry logging/editing/deleting, and progress/history/streak retrieval. Although list_goals includes today's progress inline, it clearly differs in scope from get_progress, which focuses on a single goal. No two tools appear interchangeable.
All names use snake_case consistently, and most follow a verb_noun pattern (add_goal, edit_goal, log_entry, get_progress). Minor deviation: history and streak_status are noun-only, but they remain readable and unambiguous.
With 10 tools, the set is well-scoped for a goal-tracking server. Each tool covers a necessary operation in the goal/entry lifecycle, and there is no redundant or filler tool.
The surface covers full CRUD for both goals and entries, plus derived analytics like progress, history, and streaks. No obvious gaps remain for the stated daily-goal tracking purpose.
Related MCP Connectors
Durable, user-controlled goals for AI agents, kept across any MCP client.
Work with personal goals, measurements, reviews and next actions in Results OS. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/results. Sign in to Samuelz and select your authorized workspace. An active workspace membership and the relevant module permissions are required. Review the requested permissions before authorizing. Existing approval requirements continue to apply.
Goal-based task manager for humans and AI. Read goals, add subtasks, report results.
Goal-centered work: read and write goals, tasks, notes and attachments, and decide what to do next.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables chatbots to interact with a global goals engine, allowing them to declare goals, manage branches, and evaluate outcomes through MCP tools.121MIT
- AlicenseNot gradedqualityCmaintenanceProvides MCP tools to read and update a local-first personal OS for goals, tasks, habits, food, workouts, and check-ins. Enables assistants to manage daily life data and interact with an evidence-grounded AI coach.MIT
- AlicenseNot gradedqualityDmaintenanceEnables authenticated MCP clients to manage projects, tasks, habits, and daily capacity through tool calls.8 npmISC
- AlicenseAqualityDmaintenanceEnables AI assistants to manage goals, tasks, weekly schedules, time tracking, reports, notes, and journal entries on a GoalSlot account through MCP tools.18MIT