OpenBrand MCP server
io.github.ethanjyx/openbrand·v0.1.2·808 starsExtract brand assets (logos, colors, backdrop images, brand name) from any website URL
808 stars38 downloads/wk
Reviews
Write oneNobody has reviewed OpenBrand yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
OpenBrand tools (1)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
extract_brand_assetsExtract brand assets (logos, colors, backdrop images, brand name) from a website URL. Returns structured data with logo URLs, hex colors with usage hints, backdrop/OG images, and the detected brand name.
Public scan report
scanner v0.1.10 · 2026-11-12 · same rubric, same numbers if you re-run it
- Code scan2 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 185 days ago4/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
How OpenBrand compares
Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 68/100
- higher than 30% of 875 Scraping and browsing servers
- Tools
- 1
- the typical Scraping and browsing server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 808
- more than 95% of 595 Scraping and browsing servers
- Downloads a week
- 38
- more than 13% of 355 Scraping and browsing servers with a package
What its tools let an agent do: 1 read
Install OpenBrand in Claude Code, Cursor or VS Code
Runs npx -y openbrand-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add openbrand -- npx -y openbrand-mcp
What the publisher says
From the OpenBrand repository's README, as published. We do not edit it. Read it on GitHub
OpenBrand Extract any brand from a URL
Try it out at openbrand.sh
Demo prepared with Tight Studio
Extract brand assets (logos, colors, backdrops, brand name) from any website URL.
As an API call
Get your free API key from openbrand.sh/dashboard.
cURL
curl "https://openbrand.sh/api/extract?url=https://stripe.com" \
-H "Authorization: Bearer your_api_key"TypeScript
const res = await fetch(
"https://openbrand.sh/api/extract?url=https://stripe.com",
{ headers: { Authorization: "Bearer your_api_key" } }
);
const brand = await res.json();Python
import requests
res = requests.get(
"https://openbrand.sh/api/extract",
params={"url": "https://stripe.com"},
headers={"Authorization": "Bearer your_api_key"},
)
brand = res.json()As an agent skill
Add OpenBrand to Claude Code, Cursor, Codex, Gemini CLI, and 40+ other agents:
npx skills add tight-studio/openbrandOnce installed, your agent automatically knows how to extract brand assets — just ask it to "extract brand assets from stripe.com".
As an npm package
No API key required. Runs as a library from your server-side code.
npm add openbrandimport { extractBrandAssets } from "openbrand";
const result = await extractBrandAssets("https://stripe.com");
if (result.ok) {
// result.data.brand_name → "Stripe"
// result.data.logos → LogoAsset[]
// result.data.colors → ColorAsset[]
// result.data.backdrop_images → BackdropAsset[]
} else {
// result.error.code → "ACCESS_BLOCKED" | "NOT_FOUND" | "SERVER_ERROR" | ...
// result.error.message → human-readable explanation
}As an MCP server
Use OpenBrand as a tool in Claude Code, Cursor, or any MCP-compatible client.
- Install the MCP server (no API key needed to install):
claude mcp add --transport stdio openbrand -- npx -y openbrand-mcp- Get your API key from openbrand.sh/dashboard and add it:
claude mcp add --transport stdio \
--env OPENBRAND_API_KEY=your_api_key \
openbrand -- npx -y openbrand-mcpOr add to .claude/settings.json:
{
"mcpServers": {
"openbrand": {
"command": "npx",
"args": ["-y", "openbrand-mcp"],
"env": {
"OPENBRAND_API_KEY": "your_api_key"
}
}
}
}Then ask Claude to "extract brand assets from stripe.com" and it will use the extractbrandassets tool automatically.
Self-hosting the web app
git clone https://github.com/tight-studio/openbrand.git
cd openbrand
bun install
bun devNo environment variables required. Open http://localhost:3000.
What it extracts
- Logos — favicons, apple-touch-icons, header/nav logos, inline SVGs (with dimension probing)
- Brand colors — from theme-color meta tags, manifest.json, and dominant colors from logo imagery
- Backdrop images — og:image, CSS backgrounds, hero/banner images
- Brand name — from og:site_name, application-name, logo alt text, page title
Tech stack
Next.js, React, TypeScript, Cheerio, Sharp, Tailwind CSS
License
MIT
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-11-12downgradeB → Cscore 68
OpenBrand: common questions
- Is OpenBrand MCP server safe?
- With care: it is graded C, so read the findings first (68/100). Read the OpenBrand safety report
- How do I install OpenBrand?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does OpenBrand need an API key?
- Yes. The registry entry asks for
OPENBRAND_API_KEY. - Is OpenBrand maintained?
- The last commit was 188 days ago (2026-05-12). The latest release is v0.1.2.
- What can I use instead of OpenBrand?
- Servers from other publishers that do the same job: Skyvern MCP server, three.ws Solana Memo Media MCP server and MCP server.
- How does OpenBrand compare with other Scraping and browsing MCP servers?
- safety score 68/100 (higher than 30% of 875 Scraping and browsing servers); tools 1 (the typical Scraping and browsing server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to OpenBrand
Same job from other publishers: the closest match first, then the best rated.
- SkyvernAI-powered browser automation — navigate, click, fill forms, and extract data from any website.not reviewedEstablishedA
- three.ws Solana Memo MediaExtract validated image data URIs from Solana SPL Memos and return them inline to MCP clients.not reviewedEstablishedA
- MCPScrape any website, extract structured data, and collect web content at scale with AI agentsnot reviewedEstablishedA
- TalonicExtract structured, schema-validated data from PDFs, scans, images, spreadsheets, and forms.not reviewedGrowingA
- Video ExtractDownload any video from a URL, or get its transcript and key frames. All local, no API keys.not reviewedGrowingA