Browser Use
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
Descripción del creador (original en inglés)
Clone any web page from a URL into a verified offline HTML copy, embed, or rebuild.
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
Necesitas
¿Qué app usas?
Elige tu app arriba. La recordamos, así que la próxima vez el botón dirá “Instalar en …”.
Funciona en Claude para web, escritorio y móvil:
https://webembedding-jongkos-mcp.vercel.app/mcpAbre Claude Desktop → Settings → Developer → Edit Config y pega esto en claude_desktop_config.json
{
"mcpServers": {
"web-embedding": {
"command": "npx",
"args": [
"-y",
"web-embedding",
"mcp"
]
}
}
}Ejecuta esto en tu terminal
claude mcp add --transport http web-embedding https://webembedding-jongkos-mcp.vercel.app/mcpclaude mcp add web-embedding -- npx -y web-embedding mcpPégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"web-embedding": {
"url": "https://webembedding-jongkos-mcp.vercel.app/mcp"
}
}
}Pégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"web-embedding": {
"command": "npx",
"args": [
"-y",
"web-embedding",
"mcp"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"web-embedding": {
"type": "http",
"url": "https://webembedding-jongkos-mcp.vercel.app/mcp"
}
}
}Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"web-embedding": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"web-embedding",
"mcp"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
ChatGPT solo se conecta a servidores en internet:
https://webembedding-jongkos-mcp.vercel.app/mcpLos nombres de los menús pueden variar un poco según el plan y con el tiempo.
Tu elección se guarda en una cookie en este dispositivo; no necesitas cuenta.
Esta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
Todavía no hemos leído la lista de herramientas de este servidor; revisamos los endpoints por turnos.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 6 nov 2026
El nombre en el registro se verificó con la cuenta de GitHub jongko54, dueña del repo
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Aún sin revisar; revisamos los endpoints por turnos
Aún sin revisar; revisamos los endpoints por turnos
Aún sin revisar; leemos la lista de herramientas cuando revisamos el endpoint
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 1 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
El registro no indica ninguna clave obligatoria, aunque algunos servidores te piden iniciar sesión la primera vez que los usas.
Funciona de las dos formas: instálalo en tu computadora o conéctate a la versión en la nube.
El repo de GitHub cambió por última vez –, y la última versión (0.3.12) llegó al registro hace 9 días.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. Se conecta por URL, así que también funcionan las apps que aceptan servidores MCP remotos, como ChatGPT en modo desarrollador.
En la misma categoría: Browser Use, Chrome DevTools MCP, MCP Server Browser
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
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
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
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
Solo se muestra el principio; lee el resto en el repo