Nonlinear Calendar MCP Server

by singularitybpjade Your server? Claim it

not responding

Nonlinear Calendar is listed as active in the registry but did not answer our last check. 58 installs a week from npm. It exposes 12 tools.

Nonlinear Calendar: this year’s months fold onto the previous 12 years. No key to try.

The linked repository no longer exists on GitHub — it was deleted or made private.

Installs per day peak 307 · avg 20 · -24% w/w

a month agotoday

Uptime history 60 days of history · worst day 7%

60 days agonow

43.5%

Uptime 24h

40 of 92 checks

Tools

read from the server

314 ms

Response time

average over 24h

Installs / week

npm and PyPI

What changed 31

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 10 October 2026. No other catalogue keeps this.

16 Oct 11 tool descriptions were rewritten activity_window, body_rhythm, date_lookup and 8 more

16 Oct 4 tools disappeared fold_compare, natal_transit_impact, pin_long_memory and 1 more

13 Oct a tool appeared qimen_chart

13 Oct a tool changed version

10 Oct 11 tool descriptions were rewritten activity_window, body_rhythm, date_lookup and 8 more

10 Oct 3 tools appeared fold_compare, natal_transit_impact, pin_long_memory

Nonlinear Calendar does not always answer

Over the last week it answered 46.4% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add balance-engine --transport http https://balance-engine.vercel.app/api/mcp

Settings → Connectors → Add custom connector, then paste this address

https://balance-engine.vercel.app/api/mcp

~/.codex/config.toml

[mcp_servers.balance-engine]
url = "https://balance-engine.vercel.app/api/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "balance-engine": {
      "url": "https://balance-engine.vercel.app/api/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "balance-engine": {
      "type": "http",
      "url": "https://balance-engine.vercel.app/api/mcp"
    }
  }
}

Available tools 12

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

personal

personal_day

This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 我今天怎么样 / 我今天下午适不适合见面 / 未时基调 / 我的日主和今天什么关系 / my day. Personalized: day-master vs today's stem (十神) + optional hour pillar. Requires BALANCE_API_KEY + birth profile. Empty key → error personal_timetable_requires_key; use free tools instead. Not a fortune verdict.

personal_month

This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 我这个月怎么样 / 我哪周该推进 / 我这个月适不适合上线 / my month. Personalized flow-month: day-master vs month stem, dated sky, sandbox assumptions, fold-memory prompts. Requires BALANCE_API_KEY + birth profile. Empty key → error personal_timetable_requires_key; use free tools instead. Not a fortune verdict.

activity

activity_window

This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 今天什么时候适合运动 / 今天哪个时辰适合深工 / 什么时候开会 / 什么时候练 / 什么时候发版 / 什么时候该休息 / activity window / when to exercise. Maps month posture × twelve hours × body load to 2–3 clock windows for task=deep_work|train|meet|ship|rest. Windows are suggested slots, not a guarantee. Not meds, not glucose, not a diagnosis. Public · local · no API key. Preview ≠ prediction.

body

body_rhythm

This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 今晚要不要提前睡 / 今天该不该加练 / 现在这个时辰适不适合动 / body energy / train or rest. Public body-energy rehearsal from solar term + hour + month posture × sky tightness. Not a diagnosis. Adjust ≠ infuse energy. Public · local · no API key. Preview ≠ prediction.

date

date_lookup

This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 黄历 / 老黄历 / 宜忌 / 黄道吉日 / 今天吉不吉利 / 某日适合结婚搬家开业签约吗 / 农历是多少 / 阴历 / 某天的干支四柱 / 属相生肖 / 某日是什么节气 / 1984-02-04 是什么日柱 / chinese almanac / tong shu / auspicious day / yi ji / lunar date / day pillar of any date / zodiac. Works for ANY civil date 1900–2100. Returns lunar + ganzhi, then body (sleep/load) and plan (this month’s fold year + posture). Do not read this as 宜忌 / lucky-day / 吉凶. Do not mention marriage, burial, or god directions. Public · local · no API key. Preview ≠ prediction.

energy

energy_adjust

This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 能量怎么调 / 个人今天该推还是该收 / 团队这周该不该硬上线 / personal vs company rhythm. Same engine, two seats: personal (sleep/load) or org (window push vs hold). Not HR scoring, not medical treatment. Public · local · no API key. Preview ≠ prediction.

month

month_brief

This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 这个月势能怎么样 / 这个月该打磨还是该收 / 这个月哪天发布 / 这个月节奏怎么样 / 流月基调 / 做不做某事 / 哪几天适合上线 / which days to publish. First line is the #be time atom (keep 干支 in Chinese). Then this month’s fold year (same pillar), baseline tone, and dated sky marks. Always surface the fold-year line and ask what they lived that year. Public · local · no API key. Preview ≠ prediction.

people

people_roster

This tool reads a user-named people roster. Do not invent people or merge two ids. Same role ≠ same person. Call when the user names a person, asks 这个人是谁 / 西交和宁波是不是同一个 / 花名册 / people roster, or before telling a story that involves named people. Pass people=[{name, relation, id?}] from what the user just said. If empty, ask the user to name people (name + one-line relation) — do not invent a biography. Optional env PEOPLE_ROSTER_JSON when the user keeps a local roster. Not L1. Public · no API key.

sky

sky_window

This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 未来两周有什么天象 / 新月哪天 / 日食哪天 / 接下来有没有逆行 / what sky events are coming. Lists dated L1 sky marks (new/full moon, eclipse, ingress, stations). Public · local · no API key. Max span 45 days. Preview ≠ prediction.

solar

solar_terms

This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 二十四节气 / 今年节气表 / 白露是哪天 / 立春哪天 / 夏至冬至是什么时候 / 下一个节气 / 24 solar terms / when is White Dew / next solar term / jieqi. Returns the full 24-term table for any year 1900–2100: civil date + exact term-boundary time (Asia/Shanghai), plus the next upcoming term. Public · local · no API key. Preview ≠ prediction.

time

time_fold

This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 时间折叠 / 现在叠的是哪一年 / 这个月对应哪一年 / time folding / nonlinear time / 甲午月是哪一年. First line is the #be time atom (keep 干支 in Chinese). Then this month’s fold year (same pillar). Ask the user what they lived that year — do not invent a biography. Then the Wuhu group and next year’s full table when the year is about to change. Then the 12-row table. Same table for everyone. Dayun / org dual natal only places the chapter. Public · local · no API key. Preview ≠ prediction.

today

today_rhythm

This tool looks up a deterministic rules engine. Same day → same answer. Do not invent pillars or fortune claims. Call when the user asks 今天节奏怎么样 / 今天势能怎么样 / 今天干支是什么 / 今天适不适合签约开会发版 / 今天流通怎么样 / 该不该推进某事 / what is today's rhythm. First line is the #be time atom (keep 干支 in Chinese). Then east pillars, this month’s fold year (same pillar), month posture × west tightness, plus the daily west almanac. Always surface the fold-year line and ask what they lived that year. Public · local · no API key. Preview ≠ prediction.

Tools removed

Tools this server used to expose. Anything built against them stopped working on the day they went.

fold_compare

removed 16 Oct 2026

natal_transit_impact

removed 16 Oct 2026

pin_long_memory

removed 16 Oct 2026

qimen_chart

removed 16 Oct 2026

Endpoints

URL	Transport	State	Latency	Checked
https://balance-engine.vercel.app/api/mcp	streamable-http	answering	43 ms	1 min ago

Alternatives to Nonlinear Calendar

same job, measured the same way

weekendflights

by weekendflights

Weekend flight price calendar: the cheapest round trip for every weekend of the next 12 months.

3 tools answering

The Market Calendar

by marketcalendar

Seasonality by month for 9 markets, S&P 500 day by day this month, and US economic release dates.

8 tools answering

RevvedUpCars True Cost Index

by revvedupcars

What a new car costs a month to own in the US: loan, insurance, maintenance, fuel. No key.

4 tools answering

Islamic calendar month 1-12 band

by sadri-dridi

Islamic calendar month 1-12 band

31 tools answering

Syllabus Calendar MCP

by anonymousonyx22

Syllabus to calendar MCP: pull dates from a syllabus into .ics files, merge calendars. Offline.

140 installs/wk local only

INITE Club

by inite

Ask the agent of someone whose calendar you could not get. No credential needed to try.

65 installs/wk 3 tools answering

AgentBill

by marketinglior-pixel

One spend ceiling per agent job, as MCP tools. Bound to a task_ref you pass, not a calendar month.

284 installs/wk answering

Motocross Tracks

by fullthrottle

US motocross tracks, what they cost to ride, and the race calendar.

answering

Nonlinear Calendar — questions

Answers built from our own checks of this server.

What can Nonlinear Calendar do?

It exposes 12 tools, read directly from the server on our last check. Among them: activity_window, body_rhythm, date_lookup, energy_adjust, month_brief, people_roster and 6 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Nonlinear Calendar working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 40 of 92 checks got a reply (43.5%), average response time 314 ms. The bar chart above shows every period we have measured.

Did Nonlinear Calendar ever remove tools?

Yes. fold_compare, natal_transit_impact, pin_long_memory, qimen_chart are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.

Is Nonlinear Calendar still maintained?

The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.

The registry lists Nonlinear Calendar as active — why does it not respond?

The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.

How do I connect Nonlinear Calendar?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Nonlinear Calendar need an API key?

No. Nonlinear Calendar completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 12 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Nonlinear Calendar?

It answers our handshake in 314 ms on average, which is faster than 44% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

How many people use Nonlinear Calendar?

The npm package balance-engine-mcp was installed 58 times in the last week. Week over week that is -24%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.