OpenBrandCAUTION
Extract brand assets (logos, colors, backdrops) from any website; open source alternative to Brand.dev
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
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/openbrand
Once 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 openbrand
import { 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 → ColorAsset145caaba93e4OBSERVED · 2026-09-27Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add openbrand-mcp --env OPENBRAND_API_KEY=${OPENBRAND_API_KEY} -- npx -y [email protected]Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
extract_brand_assets | read | Extract 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. |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (11 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (7)
api_url = "http://127.0.0.1"
site_url = "http://127.0.0.1:3000"
additional_redirect_urls = ["https://127.0.0.1:3000"]
# JWT issuer URL. If not set, defaults to the local API URL (http://127.0.0.1:<port>/auth/v1).
@modelcontextprotocol/sdk, tsup, typescript
@supabase/ssr, @supabase/supabase-js, @types/probe-image-size, cheerio, probe-image-size, sharp, @tailwindcss/postcss, @types/node
public/openbrand.gif
Gates applied: no_behavioural_pass.
145caaba93e4full audit observations/trust-audit/mcp-server/ethanjyx__openbrand.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-27 | 145caaba93e4 | CAUTION | B | 89 | first audit |
Questions
What is the OpenBrand MCP server?
Extract brand assets (logos, colors, backdrops) from any website; open source alternative to Brand.dev
What tools does OpenBrand expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is OpenBrand safe to connect to an agent?
With care. The audit graded it B (89/100) and found 7 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does OpenBrand need?
It reads NEXT_PUBLIC_SUPABASE_ANON_KEY, OPENBRAND_API_KEY, SUPABASE_SERVICE_ROLE_KEY and TEST_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does OpenBrand run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as openbrand at 0.2.3.
How current is this page?
The grade is for one exact copy of the source (145caaba93e4), read on 2026-09-27. The repository is watched and re-audited when it changes.