webEmbedding

io.github.jongko54Published by GitHub account jongko54v0.3.13Updated Nov 8, 2026

Clone any web page from a URL into a verified offline HTML copy, embed, or rebuild.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingBrowser AutomationDeveloper Tools

Overview

AI-generated overview

Turns a web page URL into an embed, an offline HTML snapshot, or a bounded rebuild, with read-only URL inspection tools and a local capture engine.

What you can do
  • Inspect a URL for title, metadata, frame policy and reuse route, and report runtime capabilities
  • Discover likely embed, preview, viewer, remix and source URLs on a page
  • Classify whether a reference should be embedded, sourced, captured, rebuilt or blocked, and generate an iframe snippet for frameable URLs
  • Plan a source-first reproduction path separating exact reuse from capture and rebuild work
  • Locally: capture pages with Playwright, replay network evidence, rebuild blocked pages, and self-verify against desktop, tablet and mobile screenshots
When to use it
Useful when an agent is given a URL and asked to clone, copy, recreate or embed the page, or to check whether it can be framed. Best suited to static and semi-static public pages such as marketing, documentation and landing pages.
Requirements
Remote intake endpoint needs only network access. The local stdio package (npx web-embedding mcp) needs Node.js 18 or newer, Python 3.9 or newer, and a locally installed Chrome or Chromium for Playwright capture; it does not download a browser. Authenticated runs need a caller-provided storage_state_path or user_data_dir.
Before you install
Local runs write capture artifacts, including session storage state, to caller-provided output paths. Authenticated capture requires supplying your own browser session data. The server does not bypass logins, paywalls or captchas, and reproducing a page still requires the right to do so. Telemetry is off by default and, when enabled, is sent to an endpoint you configure.

Installation

In SourceWeft

  1. Open webEmbedding in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.jongko54%2Fweb-embedding/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "webembedding": {
      "type": "http",
      "url": "https://webembedding-jongkos-mcp.vercel.app/mcp"
    }
  }
}

README

webEmbedding

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:

bash
claude mcp add web-embedding -- npx -y web-embedding@latest mcp   # Claude Codecodex 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.

[webEmbedding Skill and MCP workflow]

GitHub listing, social preview, and launch-copy recommendations are in docs/github-listing.md.

Current Status

The current pipeline is strongest for static and semi-static web pages:

  • company, brand, marketing, and documentation pages
  • public landing pages
  • iframe-blocked pages that need capture-based reconstruction
  • responsive page snapshots across desktop, tablet, and mobile

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.

Measured Checkpoints

Local benchmark runs from this repo (scripts/check_clone_quality_bench.py, mobile + tablet breakpoints, 2026-10-28):

URLPathScoreWall time
https://developer.mozilla.org/en-US/runtime snapshotroot 99, visual 100, mobile 99, tablet 99~34 s
https://lit.dev/ (web components / shadow DOM)runtime snapshotroot 99, visual 100, mobile 98, tablet 98~40 s
https://www.mozilla.org/runtime snapshotroot 95, visual 100, mobile 95, tablet 95~43 s (was ~160 s)
https://www.python.orgruntime snapshotroot 98, visual 100, mobile 98, tablet 94~226 s (was ~1011 s, failed at 73)
https://www.example.comexact reuseready 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.

Core Features

  • Source-first routing:
    • direct iframe or embed reuse when it is safe and frameable
    • original preview, export, remix, or source routes when available
    • bounded rebuild only when exact reuse is unavailable
  • Live browser capture:
    • DOM snapshot
    • runtime HTML
    • full-page screenshot
    • computed style summaries
    • CSS analysis
    • asset inventory
    • HAR-like network metadata
    • interaction states and replay traces
    • storage state export for session-aware flows
  • Blocked-site rebuild:
    • handles X-Frame-Options and CSP-blocked pages by rebuilding from captured evidence
    • generates reusable frontend reconstruction artifacts from captured page structure
    • preserves custom tags, shadow-root host structure, and semantic document structure where captured
  • Evidence limitation reporting:
    • separates directly captured artifacts from inferred or missing evidence in reproduction results and prompts
    • marks app-gated, auth-gated, and native-app-led surfaces as bounded evidence, with recommendations for user screenshots or authenticated session capture
  • Operational failure classification:
    • reports typed pipeline action codes such as network-replay-limited, auth-session-missing, public-app-gate, and canvas-visual-fallback
    • exposes HAR/network replay_readiness before treating captured network evidence as replay-grade
  • Production pipeline helpers:
    • filesystem-backed async clone job queue with durable JSON records, worker locks, retry scheduling, cancellation, and manifest annotation
    • deterministic HAR replay engine for standard HAR, near-HAR, and captured network/manifest.json artifacts
    • authenticated dashboard live corpus runner that accepts user-provided storage_state_path or user_data_dir outside the repo
  • Self-verification:
    • screenshot similarity
    • DOM snapshot similarity
    • computed-style similarity
    • hover/focus/click interaction state parity
    • interaction trace parity
    • desktop/mobile/tablet breakpoint reports
  • Responsive benchmark support:
    • primary desktop viewport: 1440x1200
    • tablet profile: 768x1024
    • mobile profile: 390x844
  • Repair loop:
    • bounded self-repair can run when the first scaffold misses the readiness threshold

Install

Requirements

  • Node.js 18 or newer
  • Python 3.9 or newer
  • Chrome or Chromium available locally for Playwright runtime capture

The 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.

Install From npm

bash
npm install -g web-embeddingweb-embedding installweb-embedding doctor

Clone a public URL after installing:

bash
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:

bash
web-embedding install --forceweb-embedding doctor

You can also run the installer without a global install:

bash
npx web-embedding install

Use As An MCP Server

For MCP clients that can launch npm stdio servers:

json
{  "mcpServers": {    "source-first-clone": {      "command": "npx",      "args": ["-y", "web-embedding@latest", "mcp"]    }  }}

For local smoke testing:

bash
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.

Hosted Apps SDK Intake Endpoint

The public remote MCP intake endpoint for Apps SDK Developer Mode is:

text
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.

Sandboxing And Approvals

webEmbedding has two different execution boundaries:

  • Hosted Apps SDK intake: read-only URL routing and classification only. It accepts absolute 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.
  • Local stdio MCP and CLI: full capture, HAR replay, queues, rebuild scaffolds, and self-verify run on the user's machine under the user's local agent and filesystem permissions. Output is written only to caller-provided paths such as output_dir or queue_root.
  • Authenticated capture: session-aware runs require the caller to intentionally provide a 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.
  • Access-controlled surfaces: paywalls, captcha flows, private dashboards, payment/checkout/account/admin flows, and native-app-led screens should be blocked, marked 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.

Agent Marketplaces

This repository includes marketplace metadata for the two local agent surfaces:

  • Codex: .agents/plugins/marketplace.json points to ./bundle/source-first-clone.
  • Claude Code: .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:

text
/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.

Install From Release

bash
curl -fsSL https://github.com/jongko54/webEmbedding/releases/latest/download/install.sh | bash

Install From This Checkout

bash
git clone https://github.com/jongko54/webEmbedding.gitcd webEmbeddingnpm installnode ./bin/web-embedding.mjs installnode ./bin/web-embedding.mjs doctor

Install Into A Temporary Home

Useful for testing without touching your real agent home:

bash
python3 python/web_embedding/installer.py install --target-home ./.tmp/homepython3 python/web_embedding/installer.py doctor --target-home ./.tmp/homepython3 python/web_embedding/installer.py uninstall --target-home ./.tmp/home

Opt-in Telemetry

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:

bash
web-embedding install --telemetry --telemetry-endpoint https://your-collector.example/events

Or manage it later:

bash
web-embedding telemetry enable --endpoint https://your-collector.example/eventsweb-embedding telemetry statusweb-embedding telemetry disableweb-embedding telemetry reset-id

Each event contains an anonymous install id, package version, command name, success/failure status, OS/runtime basics, and coarse option flags such as breakpoint_count or install_source.

Environment controls:

bash
WEB_EMBEDDING_TELEMETRY=1WEB_EMBEDDING_NO_TELEMETRY=1WEB_EMBEDDING_TELEMETRY_PROMPT=0WEB_EMBEDDING_TELEMETRY_ENDPOINT=https://your-collector.example/eventsWEB_EMBEDDING_TELEMETRY_LOG=./telemetry.jsonl

Run a local/self-hosted JSONL collector:

bash
npm run telemetry:collector -- --host 127.0.0.1 --port 8765 --out ./telemetry.jsonlWEB_EMBEDDING_TELEMETRY=1 \WEB_EMBEDDING_TELEMETRY_ENDPOINT=http://127.0.0.1:8765/events \web-embedding doctor

Summarize collected usage:

bash
npm run telemetry:summarize -- ./telemetry.jsonl

The summary includes install and clone executions, total command executions, unique anonymous install IDs, command counts, and version counts. See docs/telemetry.md for collector and analyzer details.

Quick Start

Inspect a URL and get route hints:

bash
node ./bin/web-embedding.mjs inspect \  --url https://developer.mozilla.org/en-US/

Run a safe preflight audit before capture or clone:

bash
node ./bin/web-embedding.mjs audit \  --url https://developer.mozilla.org/en-US/

The audit reports whether the reference is ready for exact/embed reuse, needs local capture, needs an authenticated session, requires manual review, or should be blocked before any browser capture or filesystem output runs.

Run the full clone workflow:

bash
node ./bin/web-embedding.mjs clone \  --url https://developer.mozilla.org/en-US/ \  --output-dir ./.tmp/mdn-clone \  --wait-seconds 2 \  --timeout-seconds 35 \  --breakpoints mobile tablet

Run a lightweight quality benchmark:

bash
python3 scripts/check_clone_quality_bench.py \  https://developer.mozilla.org/en-US/ \  --output-root ./.tmp/clone-quality-bench \  --wait-seconds 1 \  --timeout-seconds 35 \  --breakpoints mobile tablet

The benchmark prints compact rows for root, visual, and breakpoint scores. The full artifacts are written under the output directory.

CLI Commands

bash
node ./bin/web-embedding.mjs capabilitiesnode ./bin/web-embedding.mjs installnode ./bin/web-embedding.mjs doctornode ./bin/web-embedding.mjs uninstallnode ./bin/web-embedding.mjs pathsnode ./bin/web-embedding.mjs telemetry status
bash
node ./bin/web-embedding.mjs inspect --url https://www.mozilla.org/
bash
node ./bin/web-embedding.mjs audit --url https://www.mozilla.org/
bash
node ./bin/web-embedding.mjs capture \  --url https://www.mozilla.org/ \  --output-dir ./.tmp/capture-mozilla \  --breakpoints mobile tablet
bash
node ./bin/web-embedding.mjs reproduce \  --url https://www.mozilla.org/ \  --output-dir ./.tmp/reproduce-mozilla \  --breakpoints mobile tablet
bash
node ./bin/web-embedding.mjs clone \  --url https://www.mozilla.org/ \  --output-dir ./.tmp/clone-mozilla \  --breakpoints mobile tablet
bash
node ./bin/web-embedding.mjs verify \  --reference-bundle ./.tmp/reference/capture.json \  --candidate-bundle ./.tmp/candidate/capture.json

Output Artifacts

A clone run can produce:

  • capture.json
  • pipeline-run-manifest.json
  • dom/snapshot.json
  • dom/runtime.html
  • styles/computed-summary.json
  • styles/css-analysis.json
  • network/manifest.json
  • network/har.json
  • network/har-like.json
  • network/replay-report.json
  • assets/inventory.json
  • interactions/states.json
  • interactions/trace.json
  • screenshots/runtime.png
  • session/storage-state.json
  • reproduction/plan.json
  • reproduction/evidence-limitations.json
  • reproduction/rebuild-prompt.txt
  • reproduction/rebuild/starter.html
  • reproduction/rebuild/starter.css
  • reproduction/rebuild/starter.tsx
  • reproduction/rebuild/next-app/
  • reproduction/self-verify/summary.json
  • reproduction/self-verify/renderers/*/verification.json
  • reproduction/self-verify/renderers/*/visual-qa.json
  • reproduction/self-verify/renderers/*/breakpoints/*-verification.json

Quality Benchmark

Run the default small benchmark:

bash
npm run check:clone-bench:local

Run the universal route regression corpus and expectations gate:

bash
npm run check:benchmark-routes:local

Run a lightweight clone score gate:

bash
npm run check:clone-score-gate:local

Validate the committed benchmark evidence manifest:

bash
npm run check:benchmark-evidence:local

Validate production pipeline gates:

bash
npm run check:production-readiness:local

Run the operational smokes individually:

bash
npm run check:job-queue:localnpm run check:har-replay:localnpm run check:authenticated-corpus:local

Classify failure/action codes from a route report:

bash
npm run classify:pipeline-failures -- --report ./.tmp/universal-route-benchmark/universal-route-report.json

Find low-scoring persisted benchmark artifacts:

bash
npm run summarize:benchmark-scores -- --root ./.tmp --min-score 60 --max-score 70

Run specific URLs:

bash
python3 scripts/check_clone_quality_bench.py \  https://www.example.com \  https://www.mozilla.org/ \  --no-breakpoints

Run a responsive benchmark:

bash
python3 scripts/check_clone_quality_bench.py \  https://developer.mozilla.org/en-US/ \  --breakpoints mobile tablet

Development Checks

bash
python3 -m py_compile \  bundle/source-first-clone/mcp/source_first_clone/*.py \  scripts/check_integration_smoke.py \  scripts/check_clone_quality_bench.py
bash
npm run check:integration:local
bash
git diff --check

Repo Layout

  • bundle/source-first-clone Installed plugin bundle, MCP server, and exact-clone intake skill.
  • bundle/source-first-clone/mcp/source_first_clone Capture, planning, rebuild, repair, and verification engine.
  • bin/web-embedding.mjs Node CLI wrapper.
  • python/web_embedding/installer.py Shared installer and command dispatcher.
  • scripts/check_clone_quality_bench.py URL clone quality benchmark helper.
  • scripts/benchmark_routes.py Universal route/capture-depth regression benchmark helper.
  • scripts/check_benchmark_report.py Benchmark expectation validator for exact, minimum, and contains-style checks.
  • scripts/check_benchmark_evidence.py Benchmark evidence manifest validator.
  • scripts/check_job_queue_smoke.py Filesystem async clone job queue smoke test.
  • scripts/check_har_replay_smoke.py Deterministic HAR replay engine smoke test.
  • scripts/benchmark_authenticated_corpus.py User-provided authenticated dashboard corpus runner.
  • scripts/summarize_benchmark_scores.py Utility for finding low or high scoring persisted benchmark artifacts under an output root.
  • scripts/classify_pipeline_failures.py Operational failure/action taxonomy summarizer for reports and capture artifacts.
  • scripts/check_production_readiness.py Production readiness gate validator for corpus, failure taxonomy, CI wiring, and policy docs.
  • scripts/check_integration_smoke.py Release, install, and URL-only clone smoke test.
  • scripts/release_bundle.py Release artifact builder.
  • docs/ Architecture notes and universal benchmark documentation.

Positioning

The strongest claim for this project is:

A source-first website cloning engine that combines Playwright capture, HAR replay, MCP tools, and self-verification to rebuild iframe-blocked public pages with reproducible visual, DOM, style, interaction, and responsive scores.

Avoid treating the output as a legal or ownership bypass. The engine can reconstruct public page structure, but permission, licensing, and acceptable use still matter.

FAQ

How can an AI coding agent clone a website from a URL? Install the MCP server (npx -y web-embedding@latest mcp) and ask the agent to clone the URL. The agent calls clone_reference_url, which inspects the page, captures it in a real Chromium, picks reuse or rebuild, and returns the clone entrypoint with fidelity scores.

What does the clone look like on disk? For pages that block iframes, snapshot/index.html plus snapshot/assets/ is a self-contained copy of the rendered page: stylesheets inlined from source (including CSS-in-JS and adoptedStyleSheets), open shadow roots as declarative shadow DOM, canvas pixels, form state, and localized images, fonts, and SVG sprites. Serve it over HTTP (python3 -m http.server); file:// blocks external SVG <use> references.

How is this different from SingleFile, screenshot-to-code, or open-lovable? SingleFile saves a page from a browser extension or CLI; webEmbedding uses the same class of DOM serialization but runs as an MCP tool, decides between embed reuse, snapshot, and rebuild, and verifies the result at three breakpoints. Screenshot-to-code and open-lovable generate new code from an image or scrape with an LLM; webEmbedding starts from the live DOM and CSS, so text, fonts, and layout come from the source instead of being re-imagined.

What can't it clone? Server behavior (logins, payments, search, real-time data), captcha- or bot-protected pages, closed shadow roots, and canvas/WebGL apps beyond a static frame. Authenticated pages need a user-provided browser session, and you still need the right to reproduce the page.

License

MIT

Source: README.md at commit e4b1ec8

Tools

6

detect_runtime_capabilities

Detect Hosted Runtime Capabilities

Report hosted Apps SDK readiness, read-only runtime capabilities, unsupported capture behavior, and the local stdio command.

Takes no parameters.

inspect_url

Inspect URL Reuse Route

Fetch a public or user-authorized URL and inspect title, metadata, frame policy, and likely source/embed candidates. Does not capture screenshots or persist artifacts.

Parametersurlrequiredtimeout_seconds

discover_embed_candidates

Discover Embed Candidates

Extract likely embed, preview, viewer, remix, and source URLs from a public or user-authorized page.

Parametersurlrequiredtimeout_seconds

classify_clone_mode

Classify Clone Mode

Decide whether a reference should be embedded, sourced, locally captured, bounded-rebuilt, or blocked before reproduction.

Parameterscandidateslicense_textsite_profilesource_signalsexact_requested

generate_embed_snippet

Generate Embed Snippet

Generate an iframe snippet for a known frameable and authorized URL. Does not verify frameability by itself.

Parametersurlrequiredtitleframework

plan_reproduction_path

Plan Reproduction Path

Create a source-first plan that separates exact embed/source reuse from local capture and bounded rebuild work.

Parameterscandidateslicense_textsite_profilecapture_bundlesource_signalsexact_requested

Version history

3
  1. v0.3.13LatestNov 8, 2026
  2. v0.3.12Oct 29, 2026
  3. v0.3.8Sep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts