Skip to main content
Glama

Life Compass

An evidence-based reflection, goal and habit coach that runs inside your own AI.

Life Compass guides you from reflection to 1–3 goals to tiny daily habits, then keeps you going with short reviews. It's grounded in behavioural science: values work (ACT), goal setting, WOOP, implementation intentions, tiny habits, COM-B, habit-strength tracking and kind lapse handling.

It's an MCP server: you add it to an AI app you already use, and your AI becomes the coach. Your plan is a file on your computer. Nothing is sent anywhere else.

Install in one click (Claude Desktop)

  1. Download life-compass.mcpb

  2. Double-click it, or drag it into Claude Desktop (Settings → Extensions), and click Install

  3. Start a chat and say "Start my Life Compass"

No Node.js or settings needed: Claude Desktop runs it for you.

Related MCP server: mochi-quest

Other AI apps

What you need

  • Node.js 18 or newer

  • An AI app that supports MCP, for example Claude Desktop, Claude Code, Cursor, or LM Studio (for local models)

Install

Add it to your AI app. It downloads and runs with npx, so there's nothing to clone.

Claude Desktop: Settings → Developer → Edit Config, then add:

{
  "mcpServers": {
    "life-compass": { "command": "npx", "args": ["-y", "life-compass"] }
  }
}

Claude Code:

claude mcp add life-compass -- npx -y life-compass

Cursor, LM Studio and other MCP apps: add a server with command npx and arguments -y life-compass.

Restart the app.

Use it

Start a chat and say "Start my Life Compass" (or pick the life_compass prompt if your app shows prompts). Your AI will:

  1. Reflect with you, one question at a time (about 15 minutes)

  2. Help you choose 1 to 3 goals tied to your values

  3. Plan milestones and tiny habits with cues and if-then plans

  4. Help you act: say "I did my walk" and it logs it

  5. Run short reviews: "weekly review", "monthly check", "quarterly review"

Want calendar reminders? Say "export my reminders" and import the .ics file it creates.

The dashboard

A visual Compass for your plan: rings for each goal, a mountain that grows with your progress, one-tap habit tiles, what's coming up, goals with milestones, and wins.

No AI needed. The dashboard can take you through the whole method on its own: reflect one question at a time, choose goals with WOOP, break them into milestones, build tiny habits with a cue, and do the weekly, monthly and quarterly reviews. Use the + button, or Start reflecting on a new plan.

npx -y -p life-compass life-compass-ui

Or ask your AI to "open my dashboard". It runs on your computer only, at a private link with a random key; other websites can't read or change your plan. Changes you make there and through your AI show up in both.

Dashboard

Where your data lives

~/.life-compass/plan.json (change it with the LIFE_COMPASS_DIR environment variable). It's plain JSON you can read, back up or delete. A one-step backup is kept as plan.json.bak.

What's inside

File

What it is

src/method.js

The method: rules, questions and steps, each with the reason it's there

src/coach.js

Phase, what's due, capacity limits, habit strength (SRBAI), lapses

src/store.js

Local plan file, written safely

src/index.js

The MCP server: 21 tools, the life_compass prompt, and the method and plan as resources

src/web.js, src/web/

The local dashboard and its small, key-protected API

test/

End-to-end and dashboard security tests (npm test)

Not therapy

Life Compass is a self-coaching tool. If you're in crisis or struggling with your mental health, please reach out to a professional or your local emergency number.

License

MIT

Available Tools

21 tools
add_winLog a winB

Note something the person did and what changed because of it. Wins feed reviews, confidence and, for career goals, promotion cases.

Inputs: text (required), tag.

export_remindersExport calendar remindersA

Writes a calendar file (.ics) with the weekly review, the monthly habit-strength check and the quarterly review, so reminders work without any server. Returns the file path to import into a calendar app.

Inputs: time, weekday.

get_methodRead the methodA

Returns the Life Compass method: rules and, for each phase, the questions or steps in order with the reason for each. Pass a phase to get just that part.

Inputs: phase.

get_planGet the whole planB

Returns the full plan JSON (values, goals, milestones, habits, decisions, log, wins and reviews).

Inputs: no named parameters.

get_statusWhere am I?A

Call first in every session. Returns the current phase, the next reflection question, and anything due today: weekly review, monthly habit-strength checks, quarterly review, upcoming decisions and lapsed habits.

Inputs: no named parameters.

log_habitLog a habitC

Record that a habit happened (the tiny version counts). Returns the weekly streak so you can celebrate in one warm line. Never shame a gap.

Inputs: habitId (required), date, version.

monthly_checkMonthly habit-strength checkA

Record the 4 SRBAI ratings (1–5) for one habit: "I do it automatically", "without having to consciously remember", "without thinking", "before I realise I'm doing it". An average of 4 or more means it can graduate.

Inputs: habitId (required), ratings (required).

open_dashboardOpen the dashboardA

Starts the visual Life Compass dashboard on this computer (rings, mountain, habits, goals, wins) and returns a private link to open in a browser. It reads the same local plan file and stays up while this app is open.

Inputs: no named parameters.

quarterly_reviewQuarterly reviewC

30-minute reset: new life-area ratings, which goals stay, and an optional note (e.g. a gratitude letter written). Returns the change in each area since the last baseline.

Inputs: areas (required), note.

record_decisionRecord a decisionC

Close a dated decision point with what was decided.

Inputs: date (required), outcome (required).

save_baselineSave life-area ratingsA

Save 1–10 ratings for each life area. Defaults: health, career, money, relationships, home, hobbies and fun, meaning and growth; people may rename, add or remove areas. Also used at quarterly reviews.

Inputs: areas (required).

save_capacitySave time and energyB

Save realistic hours per week for the plan and current energy from 1 to 10. This caps how many habits can be active at once.

Inputs: energy (required), hoursPerWeek (required).

save_goalSave a goalB

Create or update one goal (max 3 active). Only after the person chose it. Include the value it serves, a specific statement (what, how much, by when), an identity statement and the WOOP answers.

Inputs: area (required), value (required), statement (required), id, +3 more.

save_habitSave a habitA

Create or update a tiny habit for a goal: a recipe ("After I [anchor], I will [tiny]"), its rhythm, the COM-B barrier and fix, if-then plans for obstacles and one environment change. Also use it to shrink, pause, graduate or drop a habit (status). Warns when active habits exceed what capacity allows.

Inputs: goalId (required), id, fix, full, +8 more.

save_milestonesSave milestonesA

Set a goal's milestones: 4 to 8 concrete, tickable actions spread across quarters 1–4, most in the first two. Replaces the list; ticks are kept for milestones with the same text.

Inputs: goalId (required), milestones (required).

save_plan_extrasSave decisions and low-energy ruleB

Save dated decision points (question + what to do if the answer is no) and the one-sentence low-energy rule for a bad fortnight.

Inputs: decisions, lowEnergyRule.

save_reflectionSave reflection answersA

Save answers to Phase 1 questions as the person gives them. Only include the fields answered; others are kept. Use the person's own words, lightly tidied.

Inputs: hard, name, proud, gentle, +3 more.

save_valuesSave valuesA

Save the person's 3 to 5 guiding values, each with what it means to them in their own words. Replaces the current list.

Inputs: values (required).

tick_milestoneTick a milestoneC

Mark a milestone done (or undone).

Inputs: milestoneId (required), done.

values_card_sortValues card sortA

For people unsure of their values. Returns the value cards and the steps of the sort (after the Personal Values Card Sort, Miller et al. 2001). Walk them through it, then call save_values.

Inputs: no named parameters.

weekly_reviewWeekly reviewA

5-minute weekly check-in: energy 1–10, a line on what helped or got in the way, and optionally one good thing this week and why it happened. Returns habits logged this week and a low-energy flag.

Inputs: energy (required), note, goodThing.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 21 tools

    Disambiguation4/5

    Most tools are clearly distinct: get_status/get_method/get_plan differ by what they return, and log_habit (record one occurrence) vs save_habit (configure/shrink/pause) is well separated by their descriptions. Minor overlap remains between save_baseline and quarterly_review (both record life-area ratings) and between save_milestones and tick_milestone, but descriptions give clear guidance on which to use when.

    Naming Consistency4/5

    The dominant pattern is verb_noun (get_status, save_goal, log_habit, tick_milestone, add_win, open_dashboard, export_reminders, record_decision), used consistently across the set. The review tools break the pattern as bare noun names (weekly_review, monthly_check, quarterly_review), and values_card_sort is noun-only, which are minor deviations but still readable.

    Tool Count4/5

    At 21 tools the surface is on the heavier side, but each maps to a concrete step of a multi-phase method (values, baseline, capacity, goals, milestones, habits, reviews, wins, dashboard, export). Nothing looks redundant, though the eight save_* tools reflect notable granularity that a heavier server might consolidate.

    Completeness4/5

    Coverage is broad: reading plan/status, all four planning phases, goal and habit lifecycle (including pause/graduate/drop via save_habit status), reviews, and export. The main gap is explicit goal deletion/completion and win removal, forcing agents to improvise rather than a dedicated operation.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to interact with Self, a self-awareness framework that connects daily actions to personal values, missions, and goals. Supports tracking foundations, intentions, projects, obstacles, and daily reflections through natural language.
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to act as personal growth coaches, allowing users to set goals, receive personalized daily tasks, and track progress with dynamic replanning and reward systems.
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables local-first personal growth execution where an AI agent maintains the plan and daily tasks, while the user retains control of goals and final decisions.
      15 npm
      MIT