timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Projects, context, and reports. Paid research needs Agency or your own DataForSEO login.
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 | 2026-11-13 |
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 4/5 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 Luminara Suite。按照 https://mcp.popnx.com/i/luminarasuite-suite.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 4/5 项检查 · 你的提问会经过开发者的服务器(www.luminarasuite.com) · ✓ 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
Luminara Suitehttps://www.luminarasuite.com/api/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
+ConnectorsLuminara Suite
用 Luminara Suite 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 Luminara Suite,或回答中出现 Luminara Suite 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
Luminara Suitehttps://www.luminarasuite.com/api/mcp开启新聊天,输入前先从插件列表中选择 Luminara Suite
用 Luminara Suite 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 Luminara Suite,或回答中出现 Luminara Suite 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 suite https://www.luminarasuite.com/api/mcp应能看到 Luminara Suite 在列表中并显示已连接
用 Luminara Suite 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 Luminara Suite,或回答中出现 Luminara Suite 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 Luminara Suite 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 Luminara Suite,或回答中出现 Luminara Suite 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 Luminara Suite 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 Luminara Suite,或回答中出现 Luminara Suite 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://www.luminarasuite.com/api/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user suite https://www.luminarasuite.com/api/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"suite": {
"url": "https://www.luminarasuite.com/api/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"suite": {
"type": "http",
"url": "https://www.luminarasuite.com/api/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
服务器要求先登录,才会列出它的工具。
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
发布者(luminarasuite.com)不是仓库所有者(LuminaraDigital);可能是其他人代为上架的
代码最后更新于今天
使用 AGPL-3.0
在 162 毫秒内响应(HTTP 401)
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
尚未检查;我们会在检查端点时读取工具列表
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/luminarasuite-suite)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 5 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7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 Luminara Suite | 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 | 4/5 | 5/5 | 2/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | AGPL-3.0 | 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。
Luminara Suite Open-source AI search visibility: see how your brand shows up in Google, AI Overviews, ChatGPT and Perplexity, then get a plain-English action plan.
luminarasuite.com · Quick start · Bring your own keys · Deploy · Contribute
Luminara Suite is a web app and Telegram Mini App for Answer Engine Optimization (AEO): the practice of getting your brand cited by AI answers, not just ranked by Google.
It runs on your own AI account: Groq, NVIDIA NIM or Ollama (local or cloud), with Gemini as an optional fallback. No Luminara account is needed to self-host.
Audit my website Ask a question, with plain-English rewrite and sources
Business profile that personalises every answer luminarasuite.com
Labs. OracleMind SLM Studio, the TimesFM forecaster and the Archy harness are demonstrations. Their numbers are simulated and the UI says so. They are kept for exploration, not measurement.
git clone https://github.com/LuminaraDigital/Luminara-Search-Oracle-Agent.git
cd Luminara-Search-Oracle-Agent npm ci npm run dev
Open http://localhost:3000, click the gear icon, and paste a key from one of:
| Provider | Where to get a key | Notes |
|---|---|---|
| Groq | https://console.groq.com/keys | Fastest. Default model openai/gpt-oss-120b. |
| NVIDIA NIM | https://build.nvidia.com/settings/api-keys | NVIDIA's API blocks browsers, so calls are relayed through the Worker with your key (never stored). Needs npm run cf:dev or the hosted site. |
| Ollama | Local daemon at http://127.0.0.1:11434 on the desktop app or localhost. Hosted web does not probe that address unless you save a different endpoint. Cloud keys: https://ollama.com/settings/keys | Local runs fully offline. |
| Google Gemini (optional) | https://aistudio.google.com/apikey | Fallback model, Google Search grounding, and Live Voice. |
| Tavily (optional) | https://tavily.com | Live SERP evidence for audits and chat. |
| Firecrawl (optional) | https://firecrawl.dev | Scrapes the audited site for real on-page evidence. |
Keys are stored in your browser only.
Luminara never needs your keys on its servers. In the browser build every provider is called directly from your device. Two exceptions are relayed through the Cloudflare Worker because the vendor blocks browser requests: NVIDIA NIM, and Gemini when you use the hosted key. Relayed requests carry your key in the x-provider-key header and the Worker forwards it without storing it.
On luminarasuite.com, hosted keys exist for convenience. They are only used when a request carries a valid Telegram Mini App sign-in or a verified Firebase Auth ID token, are metered per user (25 free requests per day by default), and are unlimited on a paid plan. Nobody can consume the hosted keys anonymously. Bring-your-own-key in Settings is never gated.
Audits and answers follow a published methodology rather than whatever the model improvises. The claude-seo skill set (MIT, by AgriciDaniel and contributors) is vendored under .claude/skills/ so Claude Code users of this repo get the full /seo skills, and scripts/build-playbooks.mjs compiles the methodology into services/skills/playbooks.generated.json for the app:
| Audit focus | Playbooks injected |
|---|---|
| SEO | scoring rules, technical SEO (9 categories), content quality / E-E-A-T, Schema.org status |
| AEO | scoring rules, AI search (AI Overviews, ChatGPT, Perplexity), Schema.org |
| GEO | scoring rules, AI search, content quality |
| Lenses (optional) | Local business, Online store, Content quality, Structured data, Search experience |
Reports carry a Health Score (0-100) with the playbook weights, Critical / High / Medium / Low findings, and for every recommendation a "how we'd know it failed" check and a leading indicator. Deprecation rules (no HowTo schema, FAQPage earns no rich result, INP not FID) are enforced in the prompt. Anything not observable from the scrape and search evidence is reported as "not measured".
Edit the skill files, run npm run playbooks, commit the JSON. Attribution: THIRD_PARTY_NOTICES.md.
Browser / Telegram Mini App / Windows Electron shell (React 19, Vite, Tailwind)
│ desktop loads https://luminarasuite.com (same origin as web) │ direct calls with your keys ──────────────► Groq · Ollama · Tavily · Firecrawl · Exa │ └─ /api/* ─► Cloudflare Worker (worker/) ├─ /api/providers/:id/* allow-listed proxy: BYOK relay or metered hosted keys ├─ /api/sidecars/:id/* relay to self-hosted Writing check / Results tracking ├─ /api/auth/session Telegram or Firebase identity for the current request ├─ /api/telegram/auth validates Mini App initData (HMAC-SHA256) ├─ /api/telegram/invoice Telegram Stars checkout ├─ /api/telegram/webhook bot commands, payments → KV └─ static assets the built app, SPA fallback, /desktop download page
Key files: App.tsx (shell and routing), electron/ (Windows desktop shell), services/geminiService.ts (audit and chat pipelines), services/aiProviderService.ts (Groq / NIM / Ollama with failover), services/apiClient.ts (proxy and BYOK relay), worker/ (Cloudflare Worker), services/telegram/tma.ts (Telegram bridge). Desktop guide: docs/desktop.md.
| Command | What it does |
|---|---|
npm run dev | Vite dev server on :3000 |
npm run desktop:dev | Vite + Electron against localhost (Windows shell) |
npm run desktop:dist:win | One-click NSIS installer under release/ |
npm run cf:dev | Build and run the full Worker on :8787 (copy .dev.vars.example to .dev.vars) |
npm test | Unit and integration tests (vitest) |
npm run test:coverage | Same tests with coverage report + thresholds |
npm run lint | ESLint across app and worker sources |
npm run typecheck | TypeScript, app and worker |
npm run build | Typecheck + production build |
npm run deploy | Build and wrangler deploy |
npm run tg:setup | Register webhook, menu button and commands with Telegram |
npm run secrets:check | Fail if credential-shaped strings or secret files are in the tree |
npm run prepare | Point git at .githooks (secret scan on commit and push) |
Secrets never belong in git. Use .env / .dev.vars (gitignored) and wrangler secret put for production. GitHub secret scanning, push protection, Dependabot security updates, and branch protection on main are enabled. Local hooks and CI run secrets:check as a second line of defense. After clone, run npm install once so hooks install.
npm audit, production build, bundle secret-leak guard, smoke dry-run, Wrangler staging/production dry-run..github/workflows/deploy-cloudflare.yml.not measured when evidence is missing.Built and maintained by Babatundji Williams-Fulwood (@LuminaraDigital) / Luminara Digital Agency. Product site: luminarasuite.com.
One Worker serves everything. Provider keys and the bot token live in Worker secrets only.
npx wrangler login
npx wrangler kv namespace create LUMINARA_KV # paste the id into wrangler.jsonc npx wrangler secret put BOT_TOKEN # from @BotFather npx wrangler secret put TELEGRAM_WEBHOOK_SECRET # any long random string npx wrangler secret put GROQ_API_KEY # hosted keys are optional; add the ones you offer npx wrangler secret put TAVILY_API_KEY npx wrangler secret put FIRECRAWL_API_KEY npm run deploy
Add your domain to Cloudflare first; wrangler.jsonc declares luminarasuite.com as a custom domain (change it for your own deployment). Then in @BotFather run /newbot, then /newapp with the Web App URL set to your domain, and wire the bot:
BOT_TOKEN=... TELEGRAM_WEBHOOK_SECRET=... WEBAPP_URL=https://your-domain/ npm run tg:setup
Gating is configured in wrangler.jsonc vars: REQUIRE_TG_AUTH (hosted keys need Telegram or Firebase sign-in), FIREBASE_PROJECT_ID (enables Firebase ID token verification), FREE_DAILY_LIMIT, REQUIRE_SUBSCRIPTION. Web signup/signin uses Firebase Auth (VITE_FIREBASE_* in .env); the Worker verifies tokens with Google JWKS (no Admin SDK private key). Plans and Stars prices are in worker/telegramBot.ts. Telegram's Mini App policy allows TON assets only; the TON Connect manifest is in public/.