lilt-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., "@lilt-mcp show me my open tasks due 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.
lilt-mcp
What it is
lilt-mcp is an MCP server that lets Claude read and manage your tasks and habits in Lilt, a task and habit tracker for macOS. It works with Claude Desktop, Claude Code, and any other MCP client that can launch a stdio server.
Related MCP server: Things 3 MCP Server
Requirements
macOS
Node.js 18 or later (not needed for the Claude Desktop
.mcpbbundle, which uses the app's own runtime)Lilt 1.1 or later from the Mac App Store, launched at least once
iCloud Drive turned on if you use Claude Desktop (see How it works)
Install for Claude Desktop
Download
lilt-mcp.mcpbfrom the latest GitHub release.Double-click the file, or drag it into Claude > Settings > Extensions.
Install for Claude Code
claude mcp add lilt -- npx -y lilt-mcpManual config for other MCP clients
{
"mcpServers": {
"lilt": {
"command": "npx",
"args": ["-y", "lilt-mcp"]
}
}
}If your client can't find npx, use the absolute path from which npx as the command.
Tools
Tool | What it does |
| Open tasks by default; filter by |
| Projects with open-task counts. Use these exact names for |
| Habits with today's progress, streak, and a 7-day strip. |
| title, notes, priority, due, project, plus recurrence ( |
| Mark done. Repeating tasks spawn their next occurrence. |
| Done → To Do. |
| Hide an open task until a wake time: |
| Clear a snooze; the task reappears immediately. |
| Partial edit of any field; |
| Permanent. For repeating tasks, |
| Log today, or backfill with |
Identifying a task: every mutating tool accepts either id (full UUID or a unique prefix like a1b2c3d4) or title (exact, case-insensitive; falls back to a unique partial match). Ambiguous matches return the candidates instead of guessing. Habits use id or name.
How it works
Claude ──▶ lilt-mcp ──▶ snapshot.json (READ)
└──▶ open -g "lilt://complete-task?…" (WRITE) ──▶ Lilt
└──▶ re-reads snapshot to confirm the change landedRead: Lilt writes
snapshot.json(tasks, projects, habits, with ids) after every change. Thelist_*tools read it. The server tries these paths in order:$LILT_SNAPSHOT_PATH, if set~/Library/Containers/saibuddha.Flow/Data/Library/Application Support/Lilt/snapshot.json~/Library/Application Support/Lilt/snapshot.json~/Library/Mobile Documents/iCloud~saibuddha~Flow/Documents/snapshot.json
Some MCP hosts (such as Claude Desktop) are sandboxed and can't read Lilt's app container, but can read the iCloud Drive copy in path 4. That requires iCloud Drive to be on.
Write: each mutating tool fires a
lilt://URL withopen -g(Lilt stays in the background), then polls the snapshot so the result reports what actually happened.Versions: the snapshot carries a schema
version. If Lilt and lilt-mcp disagree, tool results start with a one-line note telling you which to update.
Troubleshooting
"Lilt doesn't seem to be installed or hasn't been launched yet." No snapshot exists at any known path. Install Lilt from the Mac App Store, open it once, then try again.
"This MCP host can't read Lilt's app container, and Lilt's iCloud Drive copy isn't present." Your MCP host is sandboxed. Turn on iCloud Drive in System Settings > Apple Account > iCloud, make sure Lilt is running (Lilt 1.1 or later), then try again.
"Lilt's snapshot file is corrupted or mid-write; try again in a moment." Lilt was writing the file as it was read. Retry. If it persists, quit and relaunch Lilt.
"couldn't confirm" after a write: the URL was sent but the snapshot didn't change within 2.5 seconds. Lilt may have been asleep or just launching; run
list_tasksto check.node: command not foundin your client's logs: use the absolute path fromwhich node(orwhich npx) as thecommand.
If none of these match, the error lists every path tried and the error code for each. You can point the server at a specific file with LILT_SNAPSHOT_PATH.
Development
npm install
node index.js --help
npm run pack:mcpb # builds dist/lilt-mcp.mcpbReleasing
Bump
versionin bothpackage.jsonandmanifest.json(the pack script refuses to run if they differ).Commit and tag:
git tag v1.1.0 && git push --tags.npm publish.Run
npm run pack:mcpband attachdist/lilt-mcp.mcpbto the GitHub release.
License
MIT
Available Tools
11 toolscomplete_taskA
Mark a task done in Lilt. Identify it by id or title. If the task repeats, the next occurrence is created automatically.
Inputs: id, title.
create_taskB
Create a new task in Lilt. It lands in 'To Do' and syncs to all the user's devices via iCloud.
Inputs: title (required), due, notes, project, +6 more.
delete_taskA
Delete a task in Lilt (permanent). Identify it by id or title. For a repeating task, scope controls whether only this occurrence is removed (series continues with the next one) or the whole series ends.
Inputs: id, scope, title.
list_habitsA
List the user's habits in Lilt with today's progress, streaks, and the last 7 days. Use the [id] with log_habit.
Inputs: no named parameters.
list_projectsA
List the user's projects in Lilt with open-task counts. Use these exact names for the project parameter elsewhere.
Inputs: no named parameters.
list_tasksA
List the user's tasks in Lilt with their ids. By default shows open tasks only (To Do + In Progress). Use the returned [id] prefix with complete_task / update_task / delete_task.
Inputs: limit, status, project, overdue_only, +2 more.
log_habitA
Log a habit completion in Lilt — today by default, or a past date to backfill. Identify the habit by id or name. Omit count to add one completion; pass count to set that day's total exactly (0 clears it).
Inputs: id, date, name, count.
reopen_taskA
Move a completed task back to 'To Do'. Identify it by id or title (searches done tasks too).
Inputs: id, title.
snooze_taskA
Snooze an open task: hide it from Lilt's board, menu bar and list_tasks until a wake time. Status, due date, project and recurrence are unchanged. Pass exactly one of preset or until.
Inputs: id, title, until, preset.
unsnooze_taskA
Clear a task's snooze so it reappears in Lilt immediately. Identify it by id or title.
Inputs: id, title.
update_taskA
Edit a task in Lilt. Only the fields you pass are changed. Identify the task by id or title. Pass an empty string for due or project to clear them; pass recurrence 'none' to stop repeating.
Inputs: id, due, notes, title, +9 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Most tools map cleanly to a distinct resource+action (create/update/delete/complete/reopen/snooze/unsnooze on tasks, list/log on habits, list on projects). The only mild friction is that update_task's allowed fields are unspecified, so an agent might wonder whether status changes belong there rather than in complete_task/reopen_task. Snooze/unsnooze are explicitly delineated as out-of-band from update_task, which keeps the boundaries largely clear.
Every tool follows the same snake_case verb_noun pattern (list_projects, create_task, log_habit, unsnooze_task). Verb choice is also semantically consistent, with paired opposites (snooze/unsnooze, complete/reopen) named symmetrically.
Eleven tools is well within a comfortable range for a task/habit client. Each tool covers a genuinely distinct operation — the task lifecycle alone justifies seven of them, and no tool looks redundant or vestigial.
The task surface is essentially complete (create, list, update, delete, complete, reopen, snooze, unsnooze). However, habits only have list and log — there is no way to create, edit, or archive a habit — and projects are read-only, so agents will hit dead ends outside the task domain. Workarounds exist (habits/projects presumably managed in the Lilt app), but the surface is uneven.
Maintenance
Related MCP Connectors
Manage Superlist tasks and lists in plain language from any MCP-compatible AI agent.
Local-first task manager: create, edit, and complete tasks, projects, and checklists via MCP.
Lets Claude, ChatGPT, and Muse read and update your beckett tasks, notes, calendar, and lists.
Manage tasks, Focus Zone, notes, projects, and task history from compatible AI assistants.
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables Claude to interact with Things 3 on macOS, allowing users to create, update, and manage to-dos and projects, list tasks, search items, and navigate through Things lists using natural language.2016-
- AlicenseBqualityDmaintenanceEnables Claude to interact with Things 3 task management, allowing natural language task creation, project analysis, and GTD workflow automation.2473 PyPI44MIT
- AlicenseBqualityDmaintenanceEnables Claude to interact with task management data in the Things app, including creating tasks, managing projects, searching, and organizing priorities.211MIT
- FlicenseNot gradedqualityFmaintenanceEnables Claude Desktop and other MCP clients to manage Todoist tasks, projects, and labels through natural language.3-