tasktracker MCP server
Commit 24 Okt 2026Papan tugas berbasis local-first yang memungkinkan AI agent untuk merencanakan, memperbarui, dan melacak tugas melalui MCP dengan sistem persetujuan human-in-the-loop.
Juga dikenal sebagai Parv17k/tasktracker
- Stars
- 6
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- —
- Commit terakhir
- 24 Okt 2026
- Lisensi
- MIT
Apa itu tasktracker MCP?
tasktracker adalah MCP server. Papan tugas berbasis local-first yang memungkinkan AI agent untuk merencanakan, memperbarui, dan melacak tugas melalui MCP dengan sistem persetujuan human-in-the-loop.
Ringkasan dibuat dari README proyek
Tentang tasktracker MCP server
Mengelola workflow yang kompleks bersama AI agent adalah keunggulan utama tasktracker bagi para developer dan power user yang mengutamakan privasi. Papan tugas berbasis local-first ini menggunakan satu file SQLite untuk menyimpan semua data, memastikan tidak ada data yang keluar dari mesin Anda. Tool ini terintegrasi dengan client MCP seperti Claude Code, Cursor, dan Windsurf, menyediakan 26 specialized tools yang memungkinkan agent untuk merencanakan pekerjaan, memecah tugas menjadi subtask, mencatat progres, dan mengelola kalender.
Pengguna memegang kendali penuh melalui sistem human-in-the-loop di mana agent mengajukan perubahan yang harus menunggu persetujuan manual. Setiap modifikasi muncul sebagai permintaan dalam bahasa manusia yang dapat Anda tinjau, edit, atau abaikan dengan satu ketukan. Karena bersifat local-first, Anda dapat memasangkannya dengan Ollama atau LM Studio untuk menjaga data dan pemrosesan AI Anda tetap sepenuhnya di hardware sendiri tanpa memerlukan akun cloud atau telemetry.
Apa yang bisa Anda lakukan dengannya
- 1Automated task decompositionMinta AI agent untuk mengambil tugas tingkat tinggi dan memecahnya menjadi subtask yang lebih kecil dan mudah dikelola.
- 2Local AI task managementJalankan sistem manajemen tugas yang sepenuhnya privat menggunakan LLM lokal seperti Ollama.
- 3Voice-driven board interactionGunakan perintah suara untuk mengajukan pertanyaan kepada asisten bawaan mengenai fokus pekerjaan Anda saat ini.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Pengecekan otomatis
Berjalan 15 Nov 2026Laporan lengkap →Belum diverifikasi. Sebuah server memerlukan skor 80, tidak ada temuan serius, dan data yang cukup untuk kami periksa. Cara kerja checks · Yang perlu diperbaiki untuk menambah poin
- Source repository terhubung dan dapat dijangkauparv17k/tasktracker is public and reachablegithub.com/parv17k/tasktracker ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyaTidak diperiksa
- Provenance build (atestasi Sigstore)Tidak diperiksa
- Lisensi open source (OSI)MITspdx.org/licenses/MIT.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-10-24github.com/parv17k/tasktracker ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerTidak diperiksa
- Tidak ada advisory kritis pada paket atau dependensinyaTidak diperiksa
- Tidak ada instruksi tersembunyi untuk model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Endpoint remote merespons handshake MCPTidak diperiksa
README
Lihat di GitHubThe local-first task board for you and your AI agents.
Claude and Cursor plan and update tasks over MCP. Agents propose, you approve: every change waits for one tap. Working with agents stays low-effort: one calm board, changes in plain words, nothing leaving your machine.
A real MCP connection (a scripted demo agent) asking for three changes. Nothing moves until they're approved.
🤖 Agents work on your board
Claude Code, Cursor and any MCP client get 26 tools to plan work, book time on your calendar, break it into subtasks, log progress and finish tasks, through the same rules you use.
✅ You stay in charge
Agents propose, you approve. Changes from agents and from the built-in assistant wait on an approval card, in plain words, until you tap Apply. Trust an agent? Let it apply right away.
🏠 It stays on your machine
One SQLite file. No account, no cloud, no telemetry. Pair it with Ollama or LM Studio and even the AI runs locally.
💭 Why I built this
In the agentic AI era, the hard part isn't getting AI to do work. It's keeping up with it. Every new agent is one more thing to watch, one more place where work happens, one more stream of updates to read.
I wanted the opposite: a task board that gets calmer as AI gets more capable. One place where my agents and I share the same list, where I can see what happened at a glance, where nothing changes behind my back, and where the screen stays quiet enough to think. Task Tracker is that board.
🙋 Who it's for
| You are… | What Task Tracker gives you |
|---|---|
| A developer working with coding agents | Your agent plans the work, breaks it into subtasks, logs progress and completes tasks over MCP. You approve its changes in one tap and see everything on one board. |
| Privacy-first | Everything local: one SQLite file, no account. Run the assistant on Ollama or LM Studio and nothing leaves your machine. |
| Easily overwhelmed by tools | Four columns, no Save buttons, deadlines in plain words, and an assistant you can ask "What should I focus on today?", by typing or by voice. |
| An AI power user | Humans, the assistant and agents all go through one data layer, so the rules always match. Plan on a timeline and drag to reschedule. |
Who it's not for: teams that need shared boards and permissions, sync across devices through a cloud account, or enterprise project management with resource planning. Task Tracker is for individuals who want calm over features, local over cloud, and AI as a helper rather than a replacement.
🧘 Calm, defined
"Calm" isn't a mood here; it's a set of promises:
- Four columns to start, not a workflow designer.
- Everything autosaves. There's no Save button anywhere.
- Deadlines read like a person wrote them: Due in 3h, Overdue by 2d.
- Agents ask first. Their changes wait for your OK, spelled out in plain words, and you approve them in one tap.
- No lock states to manage: an agent's "working on it" marker expires on its own, and stale changes are flagged before you approve them.
- The assistant proposes, you approve, and it can't delete anything.
- Agents show up where you already look: on the board, live, with no extra dashboard to check.
- Each reminder fires once, and a burst arrives as a single summary.
- Errors are plain sentences with a next step, never a stack trace.
- What you don't need is folded away: undated tasks, hidden columns and the archive stay out of sight until you ask.
Quick start
git clone https://github.com/Parv17k/tasktracker.git
cd tasktracker
npm install # installs dependencies and builds the UI
npm start # → http://localhost:1717
That's it. No database to install and no config files. SQLite is built into Node 22.13+, so there's nothing native to compile either.
🤖 Work with your AI agents (MCP)
Task Tracker ships with a Model Context Protocol server, so your agent can keep track of its own work, or yours.
Claude Code
claude mcp add tasktracker -- node /absolute/path/to/tasktracker/mcp/index.js
Claude Desktop, Cursor, Windsurf and other MCP clients
{
"mcpServers": {
"tasktracker": {
"command": "node",
"args": ["/absolute/path/to/tasktracker/mcp/index.js"]
}
}
}
Then just ask:
"What's overdue across all my projects?" "Break task #3 into subtasks, tag it #backend and move it to In Progress." "Log what you just did on #12 and mark it complete." "Fit my high-priority tasks into my free time this week."
| Tool | What it does |
|---|---|
list_projects |
Every project with priority, tags, task counts per column and deadlines. A good first call |
create_project |
New project with its own board, priority, tags and optional hourly rate |
update_project |
Rename, re-icon, set priority or hourly rate, or add/remove tags |
get_board |
Columns and tasks of one project (project: "website", fuzzy) |
list_tasks |
Search across all projects or one: column, text, tag, due_within_days, overdue, archived |
get_task |
Full details, including subtask ids |
create_task |
Project, column, title, description, note (Markdown), priority, start and due dates, estimate, repeat, subtasks, tags |
update_task |
Change any field incl. estimate and repeat ("" clears dates, the estimate or the repeat), add_tags / remove_tags |
move_task |
Move by column name (fuzzy: "in prog" works) or id, or to another project |
complete_task |
Move to the done column, optionally appending a summary. A repeating task adds its next one |
archive_task |
Archive, or restore with archived: false |
append_note |
Add a timestamped line to the note (great for progress logs) |
add_subtasks |
Add checklist items |
update_subtask |
Check, uncheck or rename a subtask |
delete_subtask |
Remove a subtask |
track_time |
Start or stop the time-spent timer |
list_columns |
A project's columns with ids, hidden flags and the done column |
list_tags |
Every tag with how many tasks and projects use it |
get_request |
Whether a change request was approved, and the ids of anything it created |
claim_task |
Mark a task as being worked on (a lease, not a lock; see below) |
release_task |
Remove your "working on it" marker |
get_calendar |
Working hours, blocks (with ids), free time per day, and whether the work due fits |
plan_time |
Suggest a schedule: fits open tasks' remaining estimates into free time (priority, project, tasks, from/to). Each session is reviewed before it's booked |
block_time |
Add a meeting (busy), task time (task, with task_id) or time off (off); can repeat |
update_block |
Move or edit a block; for a repeating one, occurrence with scope: "one" or "all" |
delete_block |
Remove a block, or one occurrence of a repeating one |
✋ Agents ask first
By default, an agent can read everything but can't change your board on its own. Each write becomes a request in the 🤖 Agent requests inbox:
- A gentle toast tells you "Claude Code wants to make 3 changes"; nothing interrupts you more than that.
- Each change is spelled out in plain words, with a checkbox. Untick what you don't want, then Apply, or Dismiss the lot.
- The agent is told what happened (
get_request), including the ids of anything it created, so it can carry on. - Trust an agent? Switch the inbox to Apply right away and its changes land directly, live on the board.
🤝 When two agents touch the same card
Things stay predictable without locks to babysit:
- "Working on it" claims, not locks. An agent can mark a card it's working on; the card shows 🤖 Claude Code is working on this. Other agents still get through, but they're told, and their requests are flagged for you.
- Claims can't get stuck. They expire after 30 minutes unless the agent keeps touching the card, vanish the moment the agent disconnects, clear when the card is done or archived, and you can Release one anytime. You can always edit a claimed card yourself.
- No stale overwrites. Each request remembers the values it would replace. If you (or another agent) changed them since the agent asked, the change is flagged "The title changed since Claude Code asked" and starts unticked.
- Everything else is simple: writes are one SQLite transaction at a time, edits only touch the fields they name, and notes are append-only, so two agents logging progress both keep their lines.
The MCP server works on the same SQLite file as the app, so agents can read your board even when the web server isn't running. When it is, open tabs update live within about half a second.
✨ The built-in assistant
Click ✨ in the top bar. Connect any OpenAI-compatible provider once (one-click presets for OpenAI, OpenRouter, Groq, Ollama and LM Studio), and your board gains an assistant.
💬 Ask
- Grounded answers: every question carries a compact snapshot of your projects, columns and tasks, with deadlines, start dates, priorities, tags, subtasks and tracked time. The project you have open comes first.
- Streams as it thinks, with a Stop button. The conversation follows you between pages.
- Clear when something's wrong: if the provider is down, the key is wrong or the URL is off, you get a plain sentence and a next step, never an error dump.
✅ Act, with your approval
- Ask it to create, move, reschedule, reprioritise, tag or complete tasks, add subtasks or notes, or set up projects.
- It answers with an approval card listing each change in plain words. Untick anything you don't want, then Apply.
- Every change is checked against the same rules as the board, applied all-or-nothing, and it can't delete anything.
🎙️ Talk
- Tap the mic and speak. It stops listening when you pause. Or hold Space to talk and let go to send.
- Turn on read answers aloud 🔊 to hear the reply.
- Asked by voice? The mic reopens after each answer, for a hands-free conversation. Proposed changes pause it so you can review them.
- Uses your provider's speech models (e.g. Whisper) if you set them, or your browser's built-in speech.
🔌 Let agents do the work
- A first-class MCP server turns Task Tracker into shared memory for your coding agent.
- Agents plan (tasks and subtasks), report (timestamped notes) and finish (complete with a summary).
- Their changes appear on your board within about half a second.
- Humans, the chat and agents all go through one data layer, so the rules always match.
🔒 What leaves your machine? Only when you ask: a summary of your tasks (and, by voice, your recording) goes to the provider you chose. Your API key is stored locally and never reaches the browser, which only ever sees
…last4. Point it at Ollama or LM Studio and even that stays local.
🎯 Features
🗂️ Every project at a glance
- Totals and status breakdown for each project, with a progress ring, overdue and due-this-week counts
- Priority and tags on projects: mark what matters most, and filter the home page by tag (
work,personal,Q4…) - Coming up: everything due in the next 7 days across all projects; click a card to open that task
- Drag projects to reorder them, or sort by priority (urgent first); create, edit, archive or delete them. New projects start with four columns, or copy another project's
🗓️ Timeline: plan across time, drag to reschedule
Switch any board to Timeline. It's a Gantt chart without the clutter:
- A bar from start to deadline, or a ◆ when a task only has a deadline, grouped by column and coloured to match it
- Drag to reschedule: move a bar, drag its ends to change dates, or pull a ◆ out into a bar. Arrow keys work too, and times of day are kept
- Today is always in view; overdue items are red with "Overdue 2d"; finished ones fade
- Weeks or Months zoom, and the board's search, tag and deadline filters apply
On the home page, switch Projects to Timeline to see every project at once: one row each, with a ◆ for every deadline, so busy weeks stand out. Expand a project to see and reschedule its tasks right there.
📅 Calendar: block your time, then plan into what's free
Open Calendar from the home page (every project) or a board's Board · Timeline · Calendar switch (that project's tasks). Day, week and month views.
- Working hours for each day, with breaks (presets like Mon–Fri 9–6, lunch 1–2). Time outside them is shaded, and plans only use them.
- Block time: drag across empty time for a meeting or appointment, double-click the all-day row for time off. Drag a block to move it, pull its bottom edge to resize it. Blocks can repeat (every weekday, every week…) until a date; change or delete just one event, or the whole series.
- Book time for a task: drag it from To plan onto the calendar. It books what's left of its estimate (estimate − tracked − already booked), up to one session.
- See what fits: every day shows its free time; when more estimated work is due by a day than you have free time before it, the day says how much it's over.
- ✨ Plan my week: fits what's left of your tasks into free working time, most important first (priority, then deadline), never before a start date or after a deadline, in sessions of at most 2 hours (adjustable). The plan shows dashed; click a session to leave it out, then Book. It also says what didn't fit and which tasks need an estimate.
- Ask the assistant "fit my high-priority tasks into my free time this week", "block 2–3pm tomorrow for the dentist" or "I'm off next Friday". Every booking appears on the approval card.
- Reminders a few minutes before meetings and task time (on by default, 5–30 min).
Your calendar lives in the same local database as your tasks. It doesn't sync with Google or Apple calendars.
📋 A board that adapts to you
Columns your way
- Default columns: Open → In Progress → Follow-up → Done
- Add, rename and recolour columns, drag them by the header to reorder, and choose which one means "done"
- Removing a column that still has tasks asks first: move them elsewhere, or hide the column for later
- Smooth drag & drop with clear grab handles
Rich, frictionless cards
- Title, description, subtasks with a progress bar (drag to reorder), and a Markdown note with Mermaid diagrams
- Priority from Low to Urgent, colour tags (click one to filter the board), and an optional estimate (XS–XL or exact)
- Archive with one click (with Undo); restore or delete from the archive
- Move to another project from the panel's ⋯ menu; it keeps its status where the column names match
- Search finds text in any field, including tags
⏰ Deadlines that speak human
- Pick a date with an optional time, or a preset: Today, Tomorrow, In 2 days, Next week
- Cards read Due today, Due in 3h, Due next week or Overdue by 2d, updated live
- An optional start date turns a task into a span on the timeline
- Repeating tasks: every day, weekday, week, 2 weeks, month or year. Finish one and the next appears with its dates moved on, never already overdue
- Due this week and Overdue filters, and a start/pause time tracker on every task
⌨️ Keyboard-friendly quick add
Press N and type naturally:
Send invoice to Acme @fri !high #finance ~2h
@today@tomorrow@mon…@sun@nextweek@3d@2w@2026-12-01set the deadline!low!med!high!urgentset the priority,#financeadds a tag,~2hor~Msets the estimate- / to search, Esc to close
⏱️ Estimates and cost, only where you want them
- Size a task in one tap: XS (30m) · S (1h) · M (4h) · L (1d) · XL (3d), or type an exact amount like
90mor2.5h. - See it against reality: the panel shows "3h 10m tracked of ~4h", and the card's chip turns amber when you go over.
- Totals where they help: column headers show ~9h of estimated work, project cards show ~32h left.
- Cost, if you bill by the hour: give a project an hourly rate and currency, and estimates and tracked time turn into ~$320 est., $253 so far. No rate, no money on screen.
- Tasks without an estimate look exactly as before.
📝 Notes in Markdown, with diagrams
- Notes are formatted by default: headings, lists, tables, code, links. Click to write, Esc to finish; it autosaves.
- Checklists you can tick right in the formatted note (
- [ ] item). - Mermaid diagrams: a
```mermaidblock becomes a flowchart, sequence or Gantt diagram, themed to match. - Expand for a roomy side-by-side writer: Markdown on the left, the result on the right.
- Agents' progress logs still read one entry per line, and nothing in a note can run scripts.
🏷️ Tags that stay tidy
- Shared by tasks and projects, with suggestions as you type and a stable colour per tag
- Names ignore case, so
Designanddesignare one tag; unused tags disappear on their own - Manage tags to rename, recolour or delete one everywhere at once
📲 Install it, and get reminders
Task Tracker is a Progressive Web App: click Install in the top bar (Chrome, Edge, or Safari's Add to Dock) and it gets its own window and Dock/taskbar icon. Turn on reminders from the 🔔 bell:
| Reminder | When | Adjustable |
|---|---|---|
| The day before | at your morning time (default 9:00) | on/off, time |
| The morning it's due | at your morning time | on/off |
| Before a due time | for tasks with a time, e.g. 1 hour before | on/off, 15 min to 1 day |
| When it becomes overdue | at the due time, or the next morning for all-day tasks | on/off |
| Before a calendar block | before meetings and booked task time | on/off, 5 to 30 min |
- Works with the app closed: the local server sends reminders through the browser's push service, signed with keys generated on your machine. No account needed.
- Calm by design: each reminder fires once, done tasks never remind you, and a burst (say, after your laptop wakes) arrives as one summary.
- Click a notification to jump straight to that task.
Reminders while the app is closed need the Task Tracker server running and an internet connection for the browser's push service. Open windows also receive them over the local live-update stream.
Pertanyaan tentang tasktracker MCP
Bisakah saya menggunakan model AI lokal dengan ini?
Ya, Anda bisa memasangkannya dengan Ollama atau LM Studio sehingga proses AI pun berjalan secara lokal.
Apa yang terjadi jika agent mencoba mengubah tugas yang baru saja saya edit?
Sistem akan mendeteksi konflik dan menandai permintaan tersebut, dengan keterangan bahwa konten telah berubah sejak permintaan agent dibuat.