timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Extract a website's favicon URL (any size 16-512) via the free FaviconDL API. No API key.
Skills that teach the AI this kind of work; they work alongside this one
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
Lists are ordered by a usage score (out of 100) built from these parts
| Popularity | 9/80 | GitHub stars or weekly downloads: the larger counts 60, the smaller 20 |
|---|---|---|
| Freshness | 12/12 | Full marks for a release or code change within 30 days |
| Still answering | 0/8 | The cloud endpoint answered at the last check |
| Usage score | 21/100 |
Quality: Passed 3/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)
Pick the AI app you use, then copy the settings.
Passed 3/3 checks · Runs on your computer
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude, with some setup first
No key, nothing to install · Only the Claude desktop app (Windows or Mac), not the web or phone
Download the maker’s .mcpb file
The .mcpb file comes straight from the maker; we do not change it
Use FaviconDL and tell me what you can do for me, then show me one thing✓ If Claude says it is using FaviconDL or shows a FaviconDL tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
ChatGPT cannot connect FaviconDL yet
FaviconDL runs on your computer, but ChatGPT can only connect servers that run on the web
A · Use an app that can connect FaviconDL
B · Others in Web & browsers that work with ChatGPT
Picked from the most used in the same category, only ones that connect by address with no key
Claude Code cannot connect FaviconDL yet
The maker only provides an installer for the Claude desktop app
A · Use an app that can connect FaviconDL
Cursor cannot connect FaviconDL yet
The maker only provides an installer for the Claude desktop app
A · Use an app that can connect FaviconDL
VS Code cannot connect FaviconDL yet
The maker only provides an installer for the Claude desktop app
A · Use an app that can connect FaviconDL
mcpb: …/favicondl-mcp.mcpbBased on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Run on your computer in
ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 19, 2026
The registry name was verified with the GitHub account sweesama, which owns the repo
Code last changed yesterday
Uses MIT
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Not checked: only npm and PyPI packages with a version can be checked
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/servers/sweesama-favicondl)Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
No reviews yet
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed yesterday, and the latest version (1.0.0) reached the registry 38 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
In the same category: Browser Use, changedetection.io (official), Apify MCP Server, Pomerado, Actionbook
Same category, other makers, commands already checked. Official ones first, then by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Lets AI do web tasks for you, such as filling forms, searching and extracting data, in the maker’s cloud browsers or on your computer.
Official changedetection.io MCP: web page change tracking, back-in-stock and price alerts.
Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡
Connect your agents to any website. The cheaper, faster and more reliable alternative to browser use
Let your AI agent operate any website through a real, logged-in browser session.
| This one FaviconDL | Browser Use | changedetection.io (official) | Apify MCP Server | Pomerado | Actionbook | |
|---|---|---|---|---|---|---|
| Runs where | Installs on your computer | Cloud or install on your computer | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install |
| Needs a key | No | Yes | No | Yes | No | No |
| Add with + in Claude | No | Yes | No | No | No | No |
| Basic checks | 3/3 | 5/5 | 3/3 | 4/4 | 4/4 | 4/4 |
| License | MIT | MIT | Apache-2.0 | MIT | MIT | Apache-2.0 |
| Price | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry |
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
https://favicondl.com — 免费、快速、零成本的网站图标工具
输入网址/域名 → 抓取并下载 favicon,也可当作网站 logo 图标使用。附带图片转 favicon 工具、SEO 博客自动发布系统,支持 5 种语言。
/zh/、/ja/、/ko/、/es/)i18n/build.js 一键构建所有语言版本blog/queue.json 管理待发布关键词| 类别 | 技术 |
|---|---|
| 前端 | HTML5 + CSS3 + JavaScript (ES6+) |
| 样式 | Tailwind CSS (CDN) |
| 动画 | Anime.js |
| 图片处理 | Canvas API(纯前端) |
| ZIP 打包 | JSZip(按需加载) |
| 图标发现/代理 | Cloudflare Worker 多级发现与安全图片代理 |
| Agent 接入 | REST API + OpenAPI + llms.txt + CLI |
| MCP | 本地 stdio MCP Server(mcp/server.mjs) |
| i18n 构建 | Node.js + Cheerio |
| 博客生成 | NVIDIA NIM(OpenAI 兼容 API) |
| CI/CD | GitHub Actions |
| 数据分析 | Google Analytics 4 |
| 项目 | 方案 | 成本 |
|---|---|---|
| 托管 | Vercel 静态部署 | $0 |
| Favicon API | Vercel Function + Cloudflare Worker | $0 |
| 图片处理 | 前端 Canvas | $0 |
| CDN/代理 | Cloudflare Worker 免费额度 | $0 |
| AI 文章 | NVIDIA NIM(按当前账户额度) | 按用量 |
| 数据分析 | Google Analytics 4 | $0 |
| 总计 | $0/月 |
favicon/
├── index.html # 主页 - Favicon 获取器 ├── tools.html # 工具页面(图片转换/批量处理) ├── documentation.html # API 文档页面 ├── privacy.html # 隐私政策 ├── 404.html # 404 错误页面 ├── main.js # 主页 JavaScript ├── tools.js # 工具页 JavaScript ├── cloudflare-worker.js # Cloudflare Worker 源码(单独部署) ├── sitemap.xml # 站点地图 ├── robots.txt # 爬虫指引 │ ├── i18n/ # 多语言构建系统 │ ├── build.js # i18n 构建脚本(生成 zh/ja/ko/es 页面) │ ├── translations.js # 翻译字典(5 语言) │ └── package.json │ ├── blog/ # 博客系统 │ ├── index.html # 博客首页 │ ├── blog.css # 博客样式 │ ├── blog.js # 博客 JS(语言切换/下拉菜单) │ ├── *.html # 各篇博客文章(英文源文件) │ ├── articles.json # 文章索引(标题/描述/日期,5 语言) │ ├── queue.json # 关键词发布队列 │ └── scripts/ │ ├── generate-article.js # AI 文章生成脚本(NVIDIA NIM API) │ └── package.json │ ├── zh/ # 中文页面(i18n build 自动生成) ├── ja/ # 日本語页面 ├── ko/ # 한국어页面 ├── es/ # Español 页面 │ ├── .github/workflows/ │ └── daily-blog.yml # GitHub Actions:每日自动生成博客 ├── favicondl.ps1 # Windows PowerShell CLI 下载器 ├── favicondl.sh # Linux/macOS Bash CLI 下载器 ├── SKILL.md # Agent/OpenClaw skill canonical source ├── mcp/ # 本地 MCP Server(extract_favicon) │ ├── server.mjs │ ├── package.json │ └── README.md │ └── favicons/ # 网站自身的 favicon 资源
main 自动部署Cloudflare Worker 需要在 Cloudflare 控制台单独发布 cloudflare-worker.js。
npx serve .
python -m http.server 8080
google.com)cd i18n
npm install node build.js
会读取英文源文件 + `translations.js` 字典,自动生成 `/zh/`、`/ja/`、`/ko/`、`/es/` 下的所有页面(含博客)。
cd blog/scripts
npm install NVIDIA_API_KEY=your_key node generate-article.js
从 `queue.json` 取下一个关键词,调用 NVIDIA NIM 生成 5 语言文章,输出 HTML + 更新 `articles.json` + `sitemap.xml`。需要设置 `NVIDIA_API_KEY` 环境变量。
GitHub Actions 每天 UTC 00:00 自动执行上述流程 + i18n 构建 + commit & push。
GET https://favicondl.com/api/extract?url={域名或网址}&size={尺寸}
size 可选,范围 16–512(例如 16、32、64、128、256、512),超出范围会夹到这个区间。传入之后,跟随 302 得到的图片是恰好该边长的正方形 PNG。省略 size 则返回网站上的原始文件,已有调用不会被改成缩放图。
比原图更大的位图会用高质量重采样放大,可能发虚;SVG 会按请求尺寸栅格化。响应头 X-Favicon-Native-Size、X-Favicon-Upscaled,以及 JSON 里的 nativeWidth、nativeHeight、upscaled,用来说明原图尺寸。放大结果不会被说成清晰原图。
需要来源和候选地址时,增加 format=json。iconUrl 仍是网站上的原始文件;设置了 size 时,proxyUrl 才是那个精确尺寸的 PNG。
GET https://favicondl.com/api/extract?url=github.com&size=32&format=json
GET https://favicondl.com/api/extract?url=wikipedia.org&format=json
接口会按优先级发现 HTML 图标、SVG、Apple Touch Icon、Web Manifest 和其他安全候选,选出最大的可用源图,再按需缩放,并通过受保护的图片代理返回。部署在 Vercel Node Functions 上(sharp 做重采样)。项目提供 REST API、OpenAPI、llms.txt、CLI,以及一个调用该 API 的本地 stdio MCP Server。它不是需要单独部署的远程 MCP 服务。
.\\favicondl.ps1 -Domain "github.com" -Size 128
./favicondl.sh github.com 128
完整 Agent 说明见 SKILL.md、llms.txt 和 openapi.yaml。支持 MCP 的客户端可参考 mcp/README.md 配置本地 extract_favicon 工具。CLI 默认会带上 size=128,因此得到的是 128×128 PNG;要 32 像素就传入 32。
16–512(含 32)得到恰好 N×N 的 PNG。缩小用 Lanczos,放大用高质量重采样,非正方形用透明边补齐,SVG 按目标尺寸栅格化。省略 size 仍返回原始文件。nativeWidth、nativeHeight、upscaled、outputWidth、outputHeight;图片响应带 X-Favicon-Native-Size 与 X-Favicon-Upscaled。放大后的位图不会被描述成清晰原图。blog/queue.json 新增 30 个 pending 关键词,恢复每日自动发布。done 时会持续提示“剩余 0 篇”。本地如果未及时 git pull,可能看到旧的 pending 状态,造成误判。blog/queue.json 的 pending 数量;补充关键词后需要提交并推送到 GitHub,自动任务才会恢复。pending 关键词;调研记录见 blog/keyword-research.md。i18n/build.js 一键生成 80+ 多语言页面MIT License