webEmbedding MCP server
Commit Nov 10, 2026Clones websites by capturing DOM, styles, and assets to rebuild or reuse pages with high fidelity verification.
Also known as KeiaiLab/webEmbedding
- Stars
- 6
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 10, 2026
- License
- MIT
What is webEmbedding MCP?
webEmbedding clones websites by capturing DOM, styles, and assets to rebuild or reuse pages with high fidelity verification.
Summary generated from the project's README
About webEmbedding MCP server
Reconstructing websites by capturing DOM, styles, and assets is what webEmbedding enables for developers working with marketing sites, documentation, or landing pages. It uses Playwright to inspect a URL and determine if a page can be reused through an iframe or embed, or if it requires a bounded rebuild into HTML, CSS, or React scaffolds. This approach prioritizes original source reuse over regenerating pages from screenshots.
Users can run this as a local MCP server via stdio using npx, or as a Claude Code skill. The local installation requires Node.js 18+, Python 3.9+, and a Chrome or Chromium browser. While a read-only hosted endpoint exists for low-risk routing tasks like URL inspection and embed-snippet generation, full capture, rebuild, and verification workflows are performed locally. The system includes a filesystem-backed job queue for managing asynchronous clone tasks and provides a verification pipeline to score fidelity across visual, DOM, and interaction-state metrics.
What you can do with it
- 1Reconstruct frame-blocked pagesGenerate a React or Next.js scaffold for a website that is restricted by X-Frame-Options or CSP.
- 2Verify clone fidelityCompare a candidate page against a reference bundle using visual and computed-style checks.
- 3Audit URL reuse potentialDetermine if a specific URL can be directly embedded or if it requires a full capture workflow.
- 4Replay network trafficExecute request specifications against captured HAR files to reproduce network states.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablekeiailab/webembedding is public and reachablegithub.com/keiailab/webembedding ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-10github.com/keiailab/webembedding ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubwebEmbedding
A website cloning tool that captures live pages with Playwright and reuses the original source where it can, instead of regenerating a page from a screenshot. It ships as a CLI, an MCP server, and a Claude Code / Codex skill.
Given a URL, it inspects the page, decides whether the page can be reused directly (iframe, embed, export) or has to be rebuilt from captured evidence, captures DOM / styles / assets / network traffic, generates a bounded HTML/CSS/React scaffold when a rebuild is needed, and compares the result against the original with visual, DOM, computed-style, interaction, and responsive-breakpoint checks.
It works best on static and semi-static pages — marketing sites, landing pages, docs, and frame-blocked pages that need capture-based reconstruction. See Limitations for what it does not do.
Features
- Source-first routing — prefers direct iframe/embed reuse, then original export/preview/source, and only falls back to a bounded rebuild when reuse is unavailable.
- Live browser capture — DOM snapshot, runtime HTML, full-page screenshot, computed-style and CSS summaries, asset inventory, HAR-style network metadata, and interaction states.
- Bounded rebuild — reconstructs
X-Frame-Options/ CSP-blocked pages from captured evidence into reusablestarter.html/starter.css/starter.tsx/ Next.js scaffolds, preserving custom tags, shadow-root hosts, and semantic structure where captured. - Self-verification — screenshot, DOM, computed-style, and interaction-state similarity plus desktop/tablet/mobile breakpoint reports. Scores are generated by the verification pipeline, not hand-assigned.
- Evidence reporting — separates directly captured artifacts from inferred or missing evidence, and marks auth-gated, app-gated, and native-app surfaces as bounded.
- HAR replay — replays request specs against standard HAR, near-HAR, or captured
network/manifest.jsonartifacts. - Job queue — a filesystem-backed async clone queue with durable JSON records, worker locks, retry scheduling, and cancellation.
Requirements
- Node.js 18+
- Python 3.9+
- Chrome or Chromium for Playwright capture (the package depends on
playwright-coreand does not download a browser itself)
Installation
From npm:
npm install -g web-embedding
web-embedding install
web-embedding doctor
Or without a global install:
npx web-embedding install
As a Claude Code plugin (from the GitHub mirror):
/plugin marketplace add keiailab/webEmbedding
/plugin install source-first-clone@webembedding
Installing adds the source-first-clone plugin bundle, the exact-clone-intake skill, and
the MCP server.
Usage
CLI
# Inspect a URL and print route hints
web-embedding inspect --url https://www.mozilla.org/
# Safe preflight: is this ready for reuse, capture, a session, manual review, or blocked?
web-embedding audit --url https://www.mozilla.org/
# Full clone workflow from a single URL
web-embedding clone \
--url https://developer.mozilla.org/en-US/ \
--output-dir ./.tmp/mdn-clone \
--breakpoints mobile tablet
# Compare two capture bundles
web-embedding verify \
--reference-bundle ./.tmp/reference/capture.json \
--candidate-bundle ./.tmp/candidate/capture.json
Other subcommands: capture, reproduce, scaffold, benchmark, queue, har-replay,
capabilities, paths, telemetry, uninstall. Run web-embedding <command> --help for flags.
A clone run writes artifacts under the output directory, including capture.json, captured
dom/, styles/, assets/, network/ (with har.json and replay-report.json),
interactions/, screenshots/, and a reproduction/ tree with the rebuild scaffold and
self-verify/summary.json.
MCP server
For MCP clients that launch stdio servers over npm:
{
"mcpServers": {
"source-first-clone": {
"command": "npx",
"args": ["-y", "web-embedding@latest", "mcp"]
}
}
}
The server exposes URL inspection, capture, rebuild, verification, queue, and HAR-replay
tools, including inspect_url, audit_reference_url, classify_clone_mode,
capture_reference_bundle, build_rebuild_scaffold, clone_reference_url,
verify_fidelity_report, and replay_har_requests.
A hosted, read-only intake endpoint is also available at
https://webembedding-mcp.vercel.app/mcp. It exposes only low-risk routing tools (URL
inspection, embed-candidate discovery, clone-mode classification, embed-snippet generation) —
it does not run Playwright, read local files, or persist artifacts. Full capture, rebuild, and
clone execution are local-only through the stdio package.
Skill
The exact-clone-intake skill triggers on requests like "clone this", "copy this page
exactly", or the Korean 그대로 가져와줘 / 완전 똑같이. It drives the MCP tools in the
inspect → capture → reuse-or-rebuild → verify order. It does not handle generic URL
summarization, scraping, or any request to bypass auth, paywalls, captcha, ownership, or
license boundaries.
Telemetry
Telemetry is disabled by default. An interactive web-embedding install asks once and
defaults to No; non-interactive installs (CI, curl | bash) never prompt. If enabled, it
sends an anonymous command-completion event (install id, version, command name,
success/failure, OS/runtime basics) to a JSON endpoint you control. It never sends target
URLs, local paths, captured HTML, screenshots, storage state, environment variables, or API
keys. See docs/telemetry.md.
Limitations
This is not a full backend or app-logic clone engine. The hard boundary is server-side product behavior, not front-end evidence capture. The following are out of scope and need separate handling: login-only screens, app-first or native-app services, captcha-heavy sites, maps, games, canvas/WebGL-heavy pages, real-time feeds, payments, and booking flows.
Reconstructing a page's public structure is not a license or ownership bypass. Authenticated
capture requires the caller to intentionally provide a storage_state_path or user_data_dir;
the tool does not collect credentials or perform login bypasses, and local URL entrypoints
reject non-HTTP schemes such as file://.
Contributing
The canonical repository is on GitLab; the GitHub repository is a read-only push mirror. Please open Merge Requests on GitLab. See CONTRIBUTING.md.
License
webEmbedding MCP questions
What can the tool clone?
It works best on static and semi-static pages like marketing sites, landing pages, and documentation.
Does it bypass logins or paywalls?
No, it does not handle requests to bypass authentication, paywalls, captchas, or license boundaries.