Structured Japanese childcare facility data with source-backed facts for AI.
KIKARET is a remote MCP server published at mcp.kikaret.ai. It has been probed 11 times since 9/12/2026. It answered in 11 of them (100.0%), a near-uninterrupted record. Median response time is 2,051 ms, a delay an agent will notice. It offers a narrow, focused set of 4 tools. On the protocol side it speaks the 2026-07-28 stateless spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
ping — Parameter 'message' has no clear purpose or contextget_facility_knowledge — 'keys' parameter lacks explanation of acceptable values or formatsearch_facilities — No mention of maximum value for 'limit' parameterRisk: low
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.
pingCheck whether the KIKARET MCP server is available.
messagestringsearch_facilitiesSearch KIKARET for childcare facilities by facility name. Use this first when you do not know the facility_id. Returns facility IDs and basic location/contact information.
querystringrequiredlimitintegerget_facilityGet one KIKARET facility by facility_id. Returns facility identity, official URL, and basic resolved knowledge such as prefecture, city, address, phone, and facility type.
facility_idstringrequiredget_facility_knowledgeGet resolved KIKARET knowledge for one facility. Use facility_id from search_facilities. Optionally request specific schema keys. If keys are omitted, all resolved knowledge is returned with source metadata.
facility_idstringrequiredkeysarrayDerived 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/ai-kikaret-mcp)<a href="https://mcpmetrics.io/servers/ai-kikaret-mcp"><img src="https://mcpmetrics.io/badge/ai.kikaret/mcp/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.
Verifiable crypto signals, recorded history and always-on monitoring for AI agents via x402 on Base.
Japanese law, corporation & statistics data as MCP, normalized to English with source attribution.
Search structured COMPAMIR news in Japanese and English, with links to source reports.
**Current US rental market data for AI agents.** 1,500+ submarkets across the largest US metros, monthly-refreshed rent / vacancy / affordability / trends. Every response includes a citation back to the source — no hallucinated rent numbers. ### What you can build - **Market research agents** — *"compare 2BR rents in Austin vs Nashville"* with current, cited data - **Investment underwriting bots** — evaluate cap rates, rent growth, and vacancy across hundreds of submarkets in one conversation - **PropTech AI features** — drop into tenant portals, brokerage tools, or CRM enrichment so your agent suddenly knows real estate ### Free tier **1,000 calls / month, no credit card required.** Get an API key at [estaite.com/developers](https://estaite.com/developers). 13 tools across discovery, single-submarket analysis, comparison & ranking, and geographic queries. Streamable HTTP, MCP 2025-03-26.
One (free) MCP for the Web. Easily search, crawl, navigate, and extract websites without getting blocked. Ideal for discovering and retrieving structured insights from any public source - effortlessly and ethically. New features are live - check out what’s new: https://brightdata.com/ai/mcp-server/launch-week
Official Nordic and EU business data for AI agents — 15 countries, 11 tools. Look up companies, validate VAT, run KYB reports, screen sanctions, autocomplete addresses, resolve LEI, plus runtime discovery of 230+ endpoints. Backed by official registries (CVR, Brønnøysund, Bolagsverket, Companies House, VIES, OFAC, GLEIF, OpenSanctions).
| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-13 12:47:19 | Dual-era | 200 | 1859 | 200 | 1809 | 2026-07-28 |
| 2026-09-13 10:45:14 | Dual-era | 200 | 2711 | 200 | 2747 | 2026-07-28 |
| 2026-09-13 08:43:04 | Dual-era | 200 | 2051 | 200 | 2040 | 2026-07-28 |
| 2026-09-13 06:40:42 | Dual-era | 200 | 2734 | 200 | 2762 | 2026-07-28 |
| 2026-09-13 04:35:29 | Dual-era | 200 | 5857 | 200 | 5781 | 2026-07-28 |
| 2026-09-13 01:33:33 | Dual-era | 200 | 2207 | 200 | 2207 | 2026-07-28 |
| 2026-09-12 23:31:36 | Dual-era | 200 | 2824 | 200 | 2821 | 2026-07-28 |
| 2026-09-12 21:29:15 | Dual-era | 200 | 1831 | 200 | 1917 | 2026-07-28 |
| 2026-09-12 19:27:29 | Dual-era | 200 | 1422 | 200 | 1427 | 2026-07-28 |
| 2026-09-12 17:24:09 | Dual-era | 200 | 1898 | 200 | 1902 | 2026-07-28 |
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.