nyyon-planner
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., "@nyyon-planner Plan my day with the carry-over ritual"
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.
nyyon-planner

A local MCP server for day planning. Your AI assistant runs the planning conversation; this tool gives it memory and a method: saved day plans, weekly objectives, an honest carry-over ritual, and a rendered day card you can pin anywhere. No network, no model, nothing leaves the machine — every plan is a plain JSON file you can grep, diff, and sync however you like.
Extracted from the Daily Planner inside the Nyyon Command Center, where it plans real days.
The method (what the assistant follows)
Ground first — one
plan_daycall returns today's plan, the week's objectives, and what's still open from recent days.The carry-over ritual — unfinished items from past days surface first, and each gets a decision: done, carry over, or drop. Nothing silently disappears.
Four questions, one at a time — what do you want done today? any constraints? how many Focus Sessions fit? aligned with the week?
Focus Sessions are the backbone — ~2-hour deep-work blocks, each with one concrete deliverable (what will exist when it's done). Everything else is supporting blocks and to-dos.
Strategic or wing-it — a day either serves the week's 2-4 objectives or it deliberately doesn't. Both are legitimate; the plan says which.
The full brief ships in the server (plan_day returns it), so any MCP-capable assistant picks up the method with zero setup.
Related MCP server: AgentOS
The live panel (the part that closes the loop)
open_panel starts a tiny loopback-only web page — the day in the same aesthetic, but every control is real: tap a block or a to-do and it writes to the plan store; type a note ("replan the afternoon, I'm drained") and it's recorded. Each interaction becomes a signal, and the next plan_day call delivers all of them to the assistant exactly once as panel_activity — so the conversation always opens already knowing what you did with your hands. No fake buttons, no push magic: an honest pull on the next turn.
Loopback only, token-guarded URL, dies with the MCP process; the state is in the files either way.
Follow-up and analytics
Because every day is one JSON file with done-flags, review is just a read. review_period computes any range (defaults to the last 7 days):
completion rates — focus sessions, blocks, to-dos, and the starred few, planned vs done
the slippage list — items that appeared on multiple days before resolving, and the ones still stuck (the honest follow-up feed)
strategic vs wing-it ratio, and every touched week's objectives with their hit rate
a
review_brieftelling the assistant how to narrate the retro: lead with what shipped, read rates as patterns not grades, close by drafting next week's objectives
"Do my week in review" or "how did this month actually go" becomes one tool call plus an honest conversation.
The day card
render_plan draws any day as a clean 1080×1350 PNG — Focus Sessions accented, done items struck, the week's objectives at the foot:
Tools
tool | what it does |
| Start here. The planning brief + today's plan + the week + the carry-over feed, in one call. |
| Write the day: schedule blocks ( |
| Edit during the day — pass only the keys that change. |
| One day's plan, with its still-open items computed. |
| Recent past days with their open items — the carry-over feed. |
| Full-text search across every saved day. |
| The strategic layer: this week's 2-4 objectives. |
| Week/month analytics: completion rates, the slippage list, objectives hit rate + a retro narration brief. |
| The day as a shareable PNG day card. |
| The LIVE local page: real checkboxes + a note box; interactions surface as |
| Data dir, work week, theme — all env-overridable. |
Install (Claude / MCP)
npm install{
"mcpServers": {
"nyyon-planner": { "command": "node", "args": ["/ABSOLUTE/PATH/nyyon-planner/src/index.js"] }
}
}Or with the CLI: claude mcp add nyyon-planner -- node /ABSOLUTE/PATH/nyyon-planner/src/index.js
Settings
Everything is env-overridable (NYYON_PLANNER_*):
NYYON_PLANNER_DIR— where plans live (default~/.nyyon-planner; plain JSON, one file per day)NYYON_PLANNER_WORK_DAYS— comma list, 0=Sun..6=Sat (default1,2,3,4,5; an Israeli work week is0,1,2,3,4)NYYON_PLANNER_WEEK_START— the week's anchor day (default: first work day). Weekend days roll forward to the coming week.NYYON_PLANNER_TZ— the "today" boundary timezone (default: system)NYYON_PLANNER_PAPER / INK / MUTE / LINE / ACCENT / ACCENT_WASH— day-card colors (hex)NYYON_PLANNER_FONT_SANS / FONT_MONO / FONT_FILES— day-card fonts (IBM Plex bundled)NYYON_PLANNER_BRAND— the footer mark on the cardNYYON_PLANNER_OUT— where rendered cards are written (default<data dir>/cards)
Test
npm test # store roundtrip, week anchoring, card render — in a temp dirPart of a family
Built like nyyon-figures: a local, offline MCP server where the calling assistant does the thinking and the tool does the persistence and the drawing. MIT.
Available Tools
12 toolsget_settingsShow settingsB
The active configuration: data directory, work week (days, anchor, timezone), and day-card theme. All overridable via NYYON_PLANNER_* env vars.
Inputs: no named parameters.
list_recent_plansRecent past plansA
The most recent PAST day plans with their open (unfinished) items — the carry-over feed. Surface these at the start of planning and ask: done, carry over, or drop?
Inputs: days.
open_panelOpen the live day panelA
Start a local web panel for the day (loopback-only, token-guarded URL): REAL checkboxes for blocks, to-dos and objectives, plus a note box. Every interaction writes to the plan store and is reported back as panel_activity on the next plan_day call. Give the user the returned URL to open (or open it for them).
Inputs: date.
plan_dayStart planning a dayA
START HERE. One call returns: the planning brief (how to run the conversation), today's date, any existing plan for the day, this week's objectives, and the open items from recent days (the carry-over feed). Follow the brief, then save_plan.
Inputs: date.
read_planRead a day planA
Read one day's saved plan (schedule + to-dos + what's still open). date default today.
Inputs: date.
read_weekRead weekly objectivesB
The strategic layer: this week's 2-4 objectives (or a given week anchor date). Strategic days align to these.
Inputs: week_start.
render_planRender a day cardA
Draw a day's plan as a clean 1080x1350 PNG (Focus Sessions accented, done items struck, the week's objectives at the foot). Returns the file path — show the image inline. Great for sharing the day or pinning it somewhere visible.
Inputs: date, out_path.
review_periodReview a period (week / month analytics)A
Follow-up analytics across saved plans: per-day rollups, completion rates (focus sessions, blocks, to-dos, starred), the SLIPPAGE list (items that appeared on multiple days before resolving — and the ones still stuck), and every touched week's objectives. Defaults to the last 7 days; pass from/to for a month or any range. The result includes a review_brief telling you how to narrate it — follow it.
Inputs: to, from.
save_planSave a day planB
Write (or replace) a day's plan. schedule = time blocks; mark each ~2h Focus Session focus:true with ONE concrete deliverable. todos with star:true for the critical few. mode "strategic" (aligned to the week — set weekly_ref to the week anchor) or "wing_it".
Inputs: schedule (required), date, mode, todos, +2 more.
search_plansSearch past plansA
Full-text search across all saved day plans (summaries, blocks, to-dos). Empty query = most recent.
Inputs: limit, query.
set_weekSet weekly objectivesB
Set the week's 2-4 strategic objectives (short outcome statements, or {text, done}). week_start default = the current week's anchor.
Inputs: objectives (required), week_start.
update_planUpdate part of a day planA
Edit a plan during the day — mark blocks/to-dos done, add items, reshuffle. Pass ONLY the keys you are changing; everything else is kept.
Inputs: date, mode, todos, summary, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Each tool has a distinct purpose: configuration, daily planning (start/read/save/update/list/search), weekly objectives (read/set), visualization (render/interactive panel), and review (analytics). No two tools overlap in function; descriptions clearly differentiate them.
All tool names follow a consistent verb_noun pattern with underscores (e.g., get_settings, plan_day, save_plan, update_plan, list_recent_plans, read_week, set_week, open_panel, review_period). No mixing of conventions.
12 tools is well within the ideal range (3-15) for a planner domain. Each tool covers a necessary operation without being excessive or sparse.
The tool surface covers the core CRUD-like operations for plans and weeks, plus search, visualization, and analytics. Minor gap: no explicit delete tool, but overwriting (save_plan) serves as replacement. Overall, the set is nearly complete for its purpose.
Maintenance
Related MCP Connectors
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
Persistent, verbatim, searchable memory for AI assistants — one memory across every MCP client.
Related MCP Servers
- AlicenseBqualityDmaintenanceAn MCP server that gives AI assistants persistent memory across sessions. It stores project context, decisions, and progress in structured markdown files as well as a knowledge graph and sequential thinking for better memory storage.365 npm1MIT
- AlicenseNot gradedqualityDmaintenanceMCP server providing persistent memory, goal tracking, self-reflection, and background monitoring for any MCP-compatible AI agent.40 PyPI2MIT
- AlicenseCqualityCmaintenanceAn MCP server that gives AI coding assistants persistent memory across sessions with chain-based project tracking, tickets, and structured handoffs.42GPL 3.0
- AlicenseNot gradedqualityFmaintenanceA local MCP server that records completed tasks to daily JSONL files and promotes substantial work to a cumulative weekly Markdown worklog, providing persistent, searchable logs of AI-assisted productivity.MIT