timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Read-only search of aflink.us, a public mirror of the U.S. Air Force portal quick links.
作者提供的原文
教 AI 做这类工作的 Skill,可与本项一起使用
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
此项在“连接 AI 的应用”标签中,该标签不使用星标,按以下顺序排列
| 1. 在 Claude 连接器目录中 | 否 | |
|---|---|---|
| 2. 团队实测过 | 否 | |
| 3. 适合泰国用户 | 否 | |
| 4. 不计星标的使用量 | 20/100 | 热度 0 · 新鲜度 12 · 仍在响应 8 · 用户喜欢 +0 |
| 5. 登记日期 | 2026-11-07 |
用户喜欢: 0 · 最多加 5 分(每人 1 分),不能用钱买。
质量: 基础检查通过 4/4 项(仅展示,不用于排序)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 aflink: search AF links。按照 https://mcp.popnx.com/i/us-aflink-search.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 4/4 项检查 · 你的提问会经过开发者的服务器(api.aflink.us) · ✓ 命令已检查 2026年11月20日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
aflink: search AF linkshttps://api.aflink.us/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
+Connectorsaflink: search AF links
用 aflink: search AF links 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 aflink: search AF links,或回答中出现 aflink: search AF links 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
Plugins+Add custom MCP server
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
aflink: search AF linkshttps://api.aflink.us/mcp开启新聊天,输入前先从插件列表中选择 aflink: search AF links
用 aflink: search AF links 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 aflink: search AF links,或回答中出现 aflink: search AF links 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user search https://api.aflink.us/mcp应能看到 aflink: search AF links 在列表中并显示已连接
用 aflink: search AF links 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 aflink: search AF links,或回答中出现 aflink: search AF links 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
用 aflink: search AF links 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 aflink: search AF links,或回答中出现 aflink: search AF links 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
用 aflink: search AF links 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 aflink: search AF links,或回答中出现 aflink: search AF links 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://api.aflink.us/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user search https://api.aflink.us/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"search": {
"url": "https://api.aflink.us/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"search": {
"type": "http",
"url": "https://api.aflink.us/mcp"
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
工具名称和描述与服务器在 2026年11月17日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
search_linksSearch aflink.us for Air Force and DoD websites by name, acronym, URL, category or purpose (for example "mypay", "travel voucher", "leave"). Every word must match. Returns each link's title, URL and category, best matches (title matches) first. Links in the UNOFFICIAL category ar
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
注册名称已通过域名 aflink.us 验证(注册中心会核实域名所有权)
代码最后更新于今天
不适用:由 aflink.us 的所有者自己运行的云端服务器,你不会运行仓库里的代码
在 71 毫秒内响应(HTTP 200)
无需登录
已读取 1 个工具描述,未发现针对 AI 的隐藏指令
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/us-aflink-search)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 4 项适用的基础检查中通过了 4 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于今天,最新版本(1.0.0)于12天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同一分类中有:OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
Official Exa MCP for web search, content fetching, and multi-step research.
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
| 本项 aflink: search AF links | OpenSEO | Exa | Microsoft Learn MCP | Docs | COTAL actions (cotal.ai) | |
|---|---|---|---|---|---|---|
| 运行位置 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 是 | 是 | 是 | 否 | 否 |
| 基础检查 | 4/4 | 5/5 | 2/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | MIT | MIT | MIT | CC-BY-4.0 | NOASSERTION | Apache-2.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Cloudflare Worker behind the address-bar autocomplete (OpenSearch suggestions) for aflink.us, and aflink's public, read-only MCP server. Deployed as aflink-autocomplete and served at https://api.aflink.us; the site points at it through suggestedURL in updater.js, which the browser discovers via osdd.xml.
GET /search/{searchTerms} while the user types.[" ", [" {CATEGORY}", ...]] — the title, a zero-width space, then the category.aflink.us/?q= .src/includes/js/search.js) sees the zero-width space, searches on the title, finds the row whose title *and* category match the suggestion, and follows it.So a suggestion is only useful if the page can find the same link. Anything the worker offers that the page hides, or matches differently, is a dead suggestion — the user picks it and lands somewhere else, or nowhere.
Two things keep the two ends together, and both are load-bearing:
src/includes/js/search-match.js. The page inlines that file; this worker imports it. There is one implementation, so normalization, multi-word matching, title/URL/category matching and the ranking score cannot drift. Change matching there and both ends move together. While searching, the page lists its rows in score order, ties in page order, which is the order this worker suggests them in.src/links/ by scripts/assemble-links.js, which both builds run: updater.js for the site and its links.json, and build-links.js for this worker, which bundles the result in the links.json shape. The worker rebuilds what the page displays from it: official categories in page order (skipping isDeleted links, which the page hides), then the unofficial list.npm test in the repo root covers both — including checks that the links.json the site build actually produces is what the worker reads, and that the worker's bundle holds the same links.
Cloudflare Workers Builds deploys the worker on every push to master that touches one of its watch paths, running cd search_worker && npx wrangler deploy. Wrangler first runs the build command in wrangler.jsonc, node build-links.js, which writes src/links.generated.js (gitignored) from that commit's src/links/. So the deployed worker carries exactly the links the commit lists: nothing is fetched at request time and nothing is cached.
That only works if a link-only change triggers a build, so the watch paths (Workers & Pages → aflink-autocomplete → Settings → Build) must cover everything the worker is built from:
search_worker/*
src/links/* src/includes/js/search-match.js scripts/assemble-links.js scripts/link-status.js
A new file the worker or build-links.js imports goes on that list too. Retirement is by date (scripts/link-status.js), so a link that retires without any commit leaves the worker at the next link change; the weekly link health commit bounds that to a week.
| Change on the site | What the worker needs |
|---|---|
How search matches or ranks (normalizing, word splitting, what fields count, score) | Nothing, if the change is made in search-match.js; the worker imports it |
| A new field or source of links (another section, another JSON file) | Add it in assemble-links.js (both builds pick it up); publishedLinks(), build-links.js's slim() and to_entries() must carry it, and a new file needs a watch path |
A link becoming hidden on the page (a new flag like isDeleted) | to_entries() must filter it out too |
Renaming or restructuring links.json | to_entries() reads the new shape |
How the page resolves a chosen suggestion (?q= parsing) | The suggestion format here has to match it |
POST /mcp)The same worker is a Model Context Protocol server, so an AI agent can look up an Air Force or DoD site the way a person does on aflink.us. It is listed in the MCP Registry as us.aflink/search. The Registry verifies that name against the aflink.us domain itself (see below), and the endpoint is on the same domain, so the listing, the site and the server are visibly one publisher.
https://api.aflink.us/mcp (api.aflink.us is a Cloudflare custom domain on this worker, declared in wrangler.jsonc, that also serves the suggestions and submissions), Streamable HTTP transport (MCP spec 2025-11-25; 2025-06-18 and 2025-03-26 clients are also accepted).query (and an optional limit, 1–50, default 10) and returns matching links with title, URL, category and summary, title matches first. Links in the UNOFFICIAL category come back with official: false, and links marked as opening only from a government network with milOnly: true.links.json, and nothing else. It cannot add, change or request links; that still goes through the issue forms and their review.https://aflink.us/links.json already publishes. No login, no API key, no cookies, and the worker stores nothing about the caller.to_entries() and search() in src/index.js) and the page's own matching rules in search-match.js, so the parity rules above cover it too.It is stateless: each POST gets one JSON response, no session is kept, and GET /mcp is 405 because the server never sends anything unprompted. Any web origin may call it (CORS *), since there is nothing private to protect; an Origin that is not an http(s) origin is refused, as the transport spec asks. The code is src/mcp.js with no SDK dependency, and test/mcp-server.test.js covers the protocol, the tool and server.json.
Discovery. Besides the Registry listing, the server can be found from the domain itself, as the MCP Server Cards extension (SEP-2127) describes. src/.well-known/ai-catalog.json is served at https://aflink.us/.well-known/ai-catalog.json and lists one entry, which points to the server card at GET https://api.aflink.us/mcp/server-card, the place the spec reserves for a server at /mcp. The card (SERVER_CARD in mcp.js) gives the name, version, description and endpoint, with CORS, an ETag and an hour's caching; it does not list tools, which clients still get from tools/list. It is built in mcp.js rather than read from server.json, so the worker needs no new watch path, and a test checks the two agree. Both formats are new, so update them if the extension changes.
To try it:
claude mcp add --transport http aflink https://api.aflink.us/mcp
npx @modelcontextprotocol/inspector # transport "Streamable HTTP", the URL above
server.json in the repository root is the Registry entry. .github/workflows/mcp_publish.yml publishes it, run by hand from the Actions tab:
master. Cloudflare Workers Builds deploys the worker on every push to master that touches search_worker/, and GitHub Pages rebuilds the site; wait for both.https://api.aflink.us/mcp answers initialize as us.aflink/search at the version in server.json and that aflink.us serves the public key, then logs in and publishes.How the Registry knows aflink.us is ours. The us.aflink/* namespace is proven over HTTP: src/.well-known/mcp-registry-auth holds an Ed25519 public key (v=MCPv1; k=ed25519; p=…), served at https://aflink.us/.well-known/mcp-registry-auth, and the workflow signs its login with the matching private key. Jekyll and the Pages upload skip dot-folders, so src/_config.yml includes it and build.yml uploads hidden files; a test checks both. The private key is the MCP_REGISTRY_KEY secret of the mcp-registry-publish environment, limited to master, because it can publish anything under us.aflink/*. To rotate it, generate a new pair, replace the file and the secret, and let Pages rebuild before publishing.
The custom domain. api.aflink.us was attached once in the dashboard: adding a domain needs zone permission the Workers Builds token does not have, while a deploy that leaves an existing domain as it is needs none. wrangler.jsonc lists it so deploys keep it, and sets workers_dev: true, because a config with routes otherwise turns the workers.dev URL off. The site and getlinks.js now use api.aflink.us; the workers.dev URL stays on only for a month while traffic moves over, and is to be turned off (workers_dev: false) after 2026-12-07.
For a new listing, bump version in server.json and SERVER_VERSION in src/mcp.js together (a test checks they agree, and that the server card matches server.json), merge, let the worker build finish, and run the workflow again. The Registry refuses a version it already has.
npm install # in this directory
npm run dev # serves the worker on :8787 npm run deploy # wrangler deploy (by hand; normally Workers Builds deploys on push to master)
A development build of the site (npm run dev:build in the repo root) points its suggestions at localhost:8787, so the two can be exercised together. npm run dev bundles the links from your working copy of src/links/, so a local edit shows up when the worker restarts. npm test in the repo root bundles them too (its pretest step).
POST /submit)The same worker receives link lists from getlinks.js, run in the browser console on any AF Portal page: the script fetches every list the portal has and sends them together as { pages: [{ source, afpCategorizedLinksDto }] }. The worker starts the Portal Sync workflow (.github/workflows/portal_sync.yml), which merges the lists on the portal-sync branch and opens or updates one pull request. Nothing reaches the site until that PR is merged.
The endpoint is public, so src/submit.js is strict:
source must be one of KNOWN_SOURCES, each at most once; a new portal list is added there and to PAGES in getlinks.js.title, link, contentId and a few known fields are kept, each checked for shape and length; the whole payload is capped at 512 KB.LINKS KV namespace; an identical payload within a day is acknowledged but not re-sent.GET /submission/ ; the workflow receives only the id, because workflow_dispatch inputs are capped at 64 KB and the lists with their descriptions are larger.scripts/af-guard.js fails the run (and opens an issue) if a submission would move an existing link to a non-official domain.It needs