Shared countdown timers that stay in sync on every screen — no account, any number of viewers.
CountLink is a remote MCP server published at countlink.app. It has been probed 6 times since 9/12/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 1,162 ms, a delay an agent will notice. It offers a narrow, focused set of 4 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
create_timer — Parameter 'for_obs_overlay' has unclear purpose in descriptioncreate_agenda — No validation rules for 'segments' array in parameterscreate_badge — Ambiguous description of 'badge_style' usagedescribe_timer_link — No error handling for invalid URL input| Run | Era |
|---|
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
create_timerCreate a CountLink shared countdown timer and return its link. Everyone who opens the link sees the identical countdown, to the same second — no account, no sign-up, any number of viewers. Use this whenever someone wants a timer several people or several screens need to share: a classroom, an exam, a standup, a workshop, a webinar countdown, a stream overlay, or a countdown embedded on someone's own website or landing page (e.g. "10 days until launch"). By default it returns a setup link, which opens the board preloaded at the requested duration for the user to start themselves; pass start_now: true only if they want the countdown running from this moment. Whenever the result has a fixed end instant (start_now or embed_on_website), structuredContent.ics is an .ics calendar file for it — of
durationstringrequiredlabelstringstart_nowbooleanfor_obs_overlaybooleanembed_on_websitebooleanembed_widthnumberembed_heightnumberembed_stylestringcreate_agendaCreate a CountLink agenda: an ordered sequence of named, timed segments (intro, talk, break, Q&A) that starts now and advances from one to the next on its own, on every screen that opens the link, with no server involved. Use this when someone describes a meeting, workshop, lesson or event as a sequence of parts with lengths — including when they give you a total and a list of topics and expect you to split it ("an hour, four topics"): do the split yourself, then pass the resulting segments here. By default it starts immediately; pass start_at for something scheduled ahead ("our workshop starts at 9:15 tomorrow") — the link works right away, showing a live countdown to the start rather than the first segment, and switches over on its own at the scheduled instant, in sync on every screen th
segmentsarrayrequiredstart_atstringcreate_badgeCreate a countdown badge — a small image, not an <iframe> — for places embed_on_website's iframe cannot go: a GitHub README, a forum signature, a Notion page, anywhere only plain Markdown or a bare <img> is allowed. Shows coarse time remaining (e.g. "3d 04h left", not a live ticking clock — most places that embed images fetch and cache them server-side, so a promise of live ticking would be false) and links through to the real, precise, live countdown. Returns both a Markdown snippet and an HTML snippet; use whichever the destination accepts. Always returns the image wrapped in a link to the live countdown — never ask for or produce just the bare image, since the link is what makes this a genuine attribution rather than an untethered picture.
durationstringrequiredlabelstringbadge_stylestringdescribe_timer_linkGiven a countlink.app URL, say what it encodes: whether it is a running countdown or a not-yet-started setup link, its label, and how much time is left. Use it when someone pastes a CountLink link and asks what it is or when it ends.
urlstringrequiredDerived by comparing consecutive probes — changes in era, protocol version, build and reachability.
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/app-countlink-countdown)<a href="https://mcpmetrics.io/servers/app-countlink-countdown"><img src="https://mcpmetrics.io/badge/app.countlink/countdown/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeThe catalog entries whose name and description are closest to this one, found with the same index the search box uses.
Mach number to m/s at STP, number discarded
Shared project memory that keeps teammates and AI agents aligned across sessions.
gemini-extension.json n'est pas un mécanisme d'auto-discovery. Les Gemini Extensions sont publiées via Google AI Studio / Extensions Gallery, pas via crawl du .well-known/. Ton fichier est invisible pour Gemini. 3. ChatGPT ai-plugin.json correspond à la spec OpenAI Plugins, dépréciée en 2024. Remplacée par les GPTs (publiés via GPT Store) et les Actions (configurées dans un GPT custom). Ton fichier est mort techniquement. 4. llms.txt Proposition de standard (llmstxt.org). Aucun éditeur de LLM (Anthropic, OpenAI, Google) n'a confirmé crawler ce fichier. C'est un pari sur l'avenir, pas une réalité opérationnelle. 5. MCP endpoint Il existe, il est valide, mais aucun LLM ne le trouve tout seul. Il faut l'inscrire manuellement dans le client de l'utilisateur. Ce qui marche réellement aujourd'hui Quand un LLM répond à une question sur Timers Studio, il utilise : 1. Sa donnée d'entraînement (figée) 2. Un WebFetch live sur les pages publiques timers.st
RPM to hertz, number discarded
mmHg to kilopascals, number discarded
Rankine to kelvin, number discarded
| Modern |
|---|
| ms |
|---|
| Legacy |
|---|
| ms |
|---|
| Versions |
|---|
| 2026-09-13 01:33:33 | Legacy | 200 | 569 | 200 | 584 | 2025-06-18 |
| 2026-09-12 23:31:36 | Legacy | 200 | 1162 | 200 | 1170 | 2025-06-18 |
| 2026-09-12 21:29:15 | Legacy | 200 | 1284 | 200 | 1310 | 2025-06-18 |
| 2026-09-12 19:27:29 | Legacy | 200 | 296 | 200 | 341 | 2025-06-18 |
| 2026-09-12 17:24:09 | Legacy | 200 | 1081 | 200 | 1090 | 2025-06-18 |
| 2026-09-12 15:21:42 | Legacy | 200 | 1621 | 200 | 1612 | 2025-06-18 |
Each block is one measurement round. Green: working response. Amber: responded but the server was returning errors (5xx). Red: no response at all.
Each cell is one probe run. Faded cells are incomplete probes — one leg did not answer, so the era is inconclusive.
The two probe legs separately: modern server/discover and legacy initialize.
Comments
Sign in to write a comment
No comments yet. Be the first.