Browser Use
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
제작자가 쓴 설명(영어 원문)
Clone any web page from a URL into a verified offline HTML copy, embed, or rebuild.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
웹, 데스크톱, 모바일의 Claude에서 쓸 수 있어요:
https://webembedding-jongkos-mcp.vercel.app/mcpClaude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요
{
"mcpServers": {
"web-embedding": {
"command": "npx",
"args": [
"-y",
"web-embedding",
"mcp"
]
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add --transport http web-embedding https://webembedding-jongkos-mcp.vercel.app/mcpclaude mcp add web-embedding -- npx -y web-embedding mcp프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"web-embedding": {
"url": "https://webembedding-jongkos-mcp.vercel.app/mcp"
}
}
}프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"web-embedding": {
"command": "npx",
"args": [
"-y",
"web-embedding",
"mcp"
]
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"web-embedding": {
"type": "http",
"url": "https://webembedding-jongkos-mcp.vercel.app/mcp"
}
}
}프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"web-embedding": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"web-embedding",
"mcp"
]
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요:
https://webembedding-jongkos-mcp.vercel.app/mcp메뉴 이름은 요금제나 시기에 따라 조금 다를 수 있어요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
아직 이 서버의 도구 목록을 읽지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 6일 점검
레지스트리 이름이 GitHub 계정 jongko54 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 점검하지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요
아직 점검하지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요
아직 점검하지 않았어요. 엔드포인트를 점검할 때 도구 목록을 읽어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 1개 중 1개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.
둘 다 가능해요. 내 컴퓨터에 설치해도 되고, 클라우드 버전에 연결해도 돼요.
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(0.3.12)은 9일 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.
같은 카테고리에는: Browser Use, Chrome DevTools MCP, MCP Server Browser
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
MCP server for Chrome DevTools
MCP server for browser use access
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
webEmbedding clones any web page from its URL for AI coding agents. Give Claude Code, Codex, Cursor, or any MCP client a URL and it returns a verified clone: the original embed when the page allows it, otherwise a self-contained offline HTML snapshot (inlined CSS, shadow DOM, localized fonts and images) or a bounded rebuild, scored against desktop, tablet, and mobile screenshots of the live page.
Add it to your agent in one line:
claude mcp add web-embedding -- npx -y web-embedding@latest mcp # Claude Code
codex mcp add web-embedding -- npx -y web-embedding@latest mcp # Codex CLI
Then ask: *"Clone https://example.com into ./clone and tell me the fidelity score."* (Machine-readable summary for LLMs: llms.txt.)
webEmbedding is a source-first website cloning engine: it captures live pages with Playwright, replays network evidence from HAR artifacts, rebuilds only when direct reuse is blocked, and self-verifies the result.
It ships as a Skill + MCP server. Instead of asking a model to "clone this site" from a screenshot, it inspects the URL, chooses a reuse or rebuild route, captures DOM/runtime HTML/styles/assets/network traces, generates bounded frontend reconstruction artifacts, and checks the output with visual, DOM, computed-style, interaction, and responsive-breakpoint verification.
GitHub listing, social preview, and launch-copy recommendations are in docs/github-listing.md.
The current pipeline is strongest for static and semi-static web pages:
It is not a full backend or app-logic clone engine. Login-only screens, app-first or native-app-required services, captcha-heavy sites, maps, games, canvas/WebGL-heavy pages, real-time feeds, payments, booking flows, and private server behavior still need separate handling.
Operationally, the repo is now a production-candidate clone engine for URL-based capture and bounded reconstruction: jobs can be queued, network evidence can be replay-audited from HAR artifacts, authenticated dashboard runs can be driven from user-owned browser state, and local gates verify the route corpus, score checks, package contents, and CI wiring. The remaining hard boundary is server-side product behavior, not front-end evidence capture and reconstruction.
Local benchmark runs from this repo (scripts/check_clone_quality_bench.py, mobile + tablet breakpoints, 2026-10-28):
| URL | Path | Score | Wall time |
|---|---|---|---|
https://developer.mozilla.org/en-US/ | runtime snapshot | root 99, visual 100, mobile 99, tablet 99 | ~34 s |
https://lit.dev/ (web components / shadow DOM) | runtime snapshot | root 99, visual 100, mobile 98, tablet 98 | ~40 s |
https://www.mozilla.org/ | runtime snapshot | root 95, visual 100, mobile 95, tablet 95 | ~43 s (was ~160 s) |
https://www.python.org | runtime snapshot | root 98, visual 100, mobile 98, tablet 94 | ~226 s (was ~1011 s, failed at 73) |
https://www.example.com | exact reuse | ready yes | — |
These are generated by the local self-verify pipeline, not manually assigned ratings. Earlier bounded-rebuild previews embedded the reference screenshot, which inflated their visual score; the runtime snapshot renders real DOM and CSS, and every row above was also checked by side-by-side screenshot review. Known gap: layouts that page scripts compute for viewports other than the captured one (for example masonry footers) can still drift at tablet width. The reproducible commands and score thresholds are tracked in docs/benchmark-evidence.json. Production readiness gates are tracked in docs/production-pipeline-gates.json.
X-Frame-Options and CSP-blocked pages by rebuilding from captured evidencenetwork-replay-limited, auth-session-missing, public-app-gate, and canvas-visual-fallbackreplay_readiness before treating captured network evidence as replay-gradenetwork/manifest.json artifactsstorage_state_path or user_data_dir outside the repo1440x1200768x1024390x844The package uses playwright-core; it does not download a browser by itself.
Installing this project adds the source-first-clone plugin bundle, the exact-clone-intake skill, and the MCP server that exposes the URL inspection, capture, rebuild, and verification tools.
npm install -g web-embedding
web-embedding install web-embedding doctor
Clone a public URL after installing:
web-embedding clone \
--url https://developer.mozilla.org/en-US/ \ --output-dir ./.tmp/mdn-clone \ --wait-seconds 2 \ --timeout-seconds 35 \ --breakpoints mobile tablet
If you already have an older local plugin installed, overwrite it with:
web-embedding install --force
web-embedding doctor
You can also run the installer without a global install:
npx web-embedding install
For MCP clients that can launch npm stdio servers:
{
"mcpServers": { "source-first-clone": { "command": "npx", "args": ["-y", "web-embedding@latest", "mcp"] } } }
For local smoke testing:
npx web-embedding@latest mcp
The MCP Registry identity is io.github.jongko54/web-embedding; server.json and package.json#mcpName are kept in sync for registry ownership verification.
The public remote MCP intake endpoint for Apps SDK Developer Mode is:
https://webembedding-jongkos-mcp.vercel.app/mcp
It exposes low-risk source-first routing tools such as URL inspection, embed candidate discovery, clone-mode classification, and embed snippet generation. Full browser capture, HAR replay, queues, bounded rebuilds, and one-pass clone execution remain local-first through the stdio MCP package.
Apps SDK review pages are hosted alongside the endpoint: https://webembedding-jongkos-mcp.vercel.app/privacy.html, https://webembedding-jongkos-mcp.vercel.app/terms.html, and https://webembedding-jongkos-mcp.vercel.app/submission.html.
webEmbedding has two different execution boundaries:
http and https URLs, does not run Playwright, does not read local files, does not use browser profiles or storage state, and does not persist capture artifacts.output_dir or queue_root.storage_state_path or user_data_dir. webEmbedding does not collect credentials, perform login bypasses, or treat a public login shell as private app evidence.needs_session, or sent to manual review unless the user has explicit authorization and supplies the needed evidence.Local URL entrypoints reject non-HTTP schemes such as file:// so an agent cannot use clone/capture tools as a local file reader. Telemetry is disabled by default and, when enabled, excludes target URLs, local paths, captured HTML, screenshots, storage state, environment variables, API keys, and command output.
This repository includes marketplace metadata for the two local agent surfaces:
.agents/plugins/marketplace.json points to ./bundle/source-first-clone..claude-plugin/marketplace.json points to the same bundle and the bundle includes .claude-plugin/plugin.json.Claude Code users can add the marketplace from GitHub with:
/plugin marketplace add jongko54/webEmbedding
/plugin install source-first-clone@webembedding
AI auto-selection expectations and golden prompts live in docs/ai-distribution.md and evals/ai-selection/webembedding-golden-prompts.json.
curl -fsSL https://github.com/jongko54/webEmbedding/releases/latest/download/install.sh | bash
git clone https://github.com/jongko54/webEmbedding.git
cd webEmbedding npm install node ./bin/web-embedding.mjs install node ./bin/web-embedding.mjs doctor
Useful for testing without touching your real agent home:
python3 python/web_embedding/installer.py install --target-home ./.tmp/home
python3 python/web_embedding/installer.py doctor --target-home ./.tmp/home python3 python/web_embedding/installer.py uninstall --target-home ./.tmp/home
Telemetry is disabled by default. On an interactive first install, web-embedding install asks once and defaults to No. Non-interactive installs such as CI and curl | bash do not prompt. If you opt in, web-embedding sends a small anonymous command-completion event to a JSON POST endpoint you control. It does not send target URLs, local paths, captured HTML, screenshots, storage state, environment variables, API keys, or command output.
Enable it during install:
web-embedding install --telemetry --telemetry-endpoint https://your-collector.example/events
Or manage it later:
web-embedding telemetry enable --endpoint https://your-collector.example/events
web-embeddin
앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요