io.github.shibley由 GitHub 帳號 shibley 發布v0.2.3更新於 Oct 25, 2026
Live status probes plus published uptime and incident history for 280+ APIs and cloud services.
遠端 MCP 伺服器，讓助理查詢 280 多個雲端 API 與服務的即時狀態、可用率歷史與廠商事故記錄。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.shibley%2Fapistatuscheck/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"api-status-check": {
"type": "http",
"url": "https://apistatuscheck.com/api/mcp"
}
}
}An MCP (Model Context Protocol) server for checking real-time operational status of 285 cloud services and APIs directly from AI coding assistants.
AWS, GitHub, Stripe, OpenAI, Vercel, Cloudflare, Datadog, PagerDuty, Twilio, Shopify, Slack, Zoom, and 270+ more. Full list at apistatuscheck.com.
The server is also hosted, so the fastest path is the remote Streamable HTTP
endpoint. This is the same entry the official MCP Registry advertises as
io.github.shibley/apistatuscheck.
For stdio-only clients:
Broken on published version
0.1.0. That tarball'sdist/index.jsshipped without a#!/usr/bin/env nodeshebang, so the shim was executed byshinstead of Node and the command failed withcommand not found. Fixed in this repo (shebang added, plus anapistatuscheck-mcp-serverbin alias so the command matches the package name), but the fix is not on npm yet —0.1.1needs to be published. Until then, build from source:
Add to your claude_desktop_config.json. This points at the hosted endpoint —
do not use "args": ["-y", "apistatuscheck-mcp-server"], because the only version
on npm (0.1.0) is the broken one described above and fails silently.
Same hosted endpoint via mcp-remote:
MIT — Bity LLC
來源：README.md，提交 a51dd62
List monitored APIs
List the APIs and developer platforms this service monitors, optionally filtered by category. Statuses come from the most recently published monitor snapshot, not a live probe, and can be up to a day old — check monitorCheckedAt, and call get_api_status when the caller needs the status right now.
limitcategorySearch monitored APIs
Find monitored APIs by name, slug, category or description. Use this to resolve a product name the user mentioned into the slug the other tools take.
limitquery必填Check an API right now
Probe a monitored API endpoint at call time and return up/degraded/down with the response time. This is the tool to reach for when a user asks "is X down?" — it makes a real request rather than reading the hourly cache.
slug必填List APIs currently down or degraded
Everything the most recent monitor run found down or degraded, across all categories. Returns an empty list when the monitor snapshot is missing or stale — an empty list is therefore not proof that everything is healthy; check monitorLastRun.
無需輸入參數。
Get retained uptime history
Uptime percentages, response-time stats and recorded data points for one API over a time range. History is retained for 30 days; an API added recently will have few or no data points, which reads as null percentages rather than 100%.
slug必填rangeGet a service’s published incident history
Real incidents a vendor published on its own status page, newest first, with start/end times, duration, severity, affected components and a link to the vendor’s incident page. Use this for "has X been flaky lately?" — it is the vendor’s own record, not our probes. Services without a public Statuspage endpoint return covered:false rather than an empty list.
limitwindowservice必填Rank vendors by reliability
Given several service slugs, return a scorecard ranked worst-first: incident count, total downtime minutes, mean time to resolve, and the longest incident over a window. Use this to answer "which vendor in my stack is least reliable?" — it compares services across vendors, which a vendor’s own monitoring tool cannot. Services with no archive are listed separately as uncovered instead of being ranked as flawless.
windowservices必填List API categories
Category slugs and how many monitored APIs sit in each. Use the slugs with list_apis.
無需輸入參數。
已滿足適用檢查項的 100%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
tattoo.check官方發布者
check.tattoo: tattoo size and placement guide 的託管 MCP 服務，由 check.tattoo 發布；無需登入；Streamable HTTP；5 個工具。
pt.iva官方發布者
在 VIES 中驗證歐盟增值稅號，並回傳葡萄牙增值稅法典（CIVA）與 RITI 條文，支援葡語與英語。
由 GitHub 帳號 throttler300 發布
一個本機 MCP 伺服器，把助理的引用綁定到已准入的來源文字並標註片段位置，可選擇拒絕雜湊已過期的引用。
由 GitHub 帳號 kriton-dev 發布
託管於 Apify 的遠端 MCP 伺服器，讓助理檢查網站宣告的七類 HTTP 安全標頭，且不傳回原始標頭值。
由 GitHub 帳號 Voopa-Corp 發布
對照創作要求審查已生成的影片，在再次付費算圖前建議是剪輯修改、重試一次還是更換做法。
claude mcp add --transport http apistatuscheck https://apistatuscheck.com/api/mcpnpx -y mcp-remote https://apistatuscheck.com/api/mcpnpx -y apistatuscheck-mcp-servergit clone https://github.com/shibley/apistatuscheck-mcp-server.gitcd apistatuscheck-mcp-server && npm install && npm run buildnode dist/index.jsdocker build -t apistatuscheck-mcp .docker run -i apistatuscheck-mcp{ "mcpServers": { "apistatuscheck": { "command": "npx", "args": ["-y", "mcp-remote", "https://apistatuscheck.com/api/mcp"] } }}{ "mcpServers": { "apistatuscheck": { "command": "npx", "args": ["-y", "mcp-remote", "https://apistatuscheck.com/api/mcp"] } }}git clone https://github.com/shibley/apistatuscheck-mcp-server.gitcd apistatuscheck-mcp-servernpm installnpm run buildnode dist/index.js