data-liberation-agent
Extract content from closed web platforms into WordPress-compatible WXR files.
The problem
Closed platforms make it hard to leave. Wix has no HTML export and caps RSS at 20 posts. JavaScript-rendered content and limited APIs leave your site data locked inside.
The solution
This tool extracts all content from closed platforms — posts, pages, media, navigation, redirects, products — and produces a standard WordPress WXR file ready to import.
Where to host WordPress: If your current provider also offers WordPress, you can move to WordPress and stay with them. WordPress.com is another option: the $4/mo Personal plan now supports plugins and themes, and the WordPress.com MCP integration gives AI agents direct write access.
Supported platforms
All eight platforms have MCP adapters with full extraction support including products (exported as WooCommerce-compatible CSV). GoDaddy Websites & Marketing is pages + blog only in v1; GoDaddy Online Store (OLS) product support is planned for v1.1.
AI tool integration
Claude Code
As a marketplace & plugin from GitHub
# Install from GitHub
claude plugin marketplace add Automattic/data-liberation-agent
claude plugin install data-liberation
# Use from the git checkout
cd data-liberation-agent
claude --add-plugin .
This installs the MCP server and skills directly.
Gemini CLI
# Use from the git checkout
cd data-liberation-agent
gemini extension link .
Codex
cd data-liberation-agent
codex
The .codex-plugin/plugin.json and .mcp.json register the MCP server and skills automatically.
Any MCP client
npx tsx src/mcp-server.ts
# or
npm run mcp
Stdio transport. Exposes 11 tools: liberate_detect, liberate_discover, liberate_inspect, liberate_extract, liberate_status, liberate_qa, liberate_map_apis, liberate_probe, liberate_verify, liberate_setup, and liberate_import.
Quick start
# 1. Install
npm install
# 2. Extract a site (works for any supported platform). A local preview site
# boots automatically after extraction — Automattic Studio if installed,
# WordPress Playground otherwise.
npm run liberate -- https://yoursite.com
# 3. Re-open the preview later (same Studio/Playground selection as above)
npm run liberate -- preview ./output/yoursite.com --open
# 4. Or just the inspection
npm run inspect -- https://yoursite.com
# 5. Verify extraction quality
npm run verify -- ./output/yoursite.com
# 6. Validate WordPress connection
npm run setup -- --site your-wp-site.wordpress.com --username you --token YOUR_APP_PASSWORD
# 7. Import to WordPress
npm run liberate -- import ./output/yoursite.com/output.wxr --site your-wp-site --username you --token YOUR_APP_PASSWORD
Or skip all of that and paste the prompt into your AI assistant — it will handle everything.
Output
A successful extraction produces in /output/<site>/:
output/<site>/
output.wxr — WordPress eXtended RSS file, ready to import via WordPress Admin > Tools > Importmedia/ — downloaded images and attachments with local paths rewritten in the WXRredirect-map.json — old platform paths mapped to new WordPress slugsextraction-log.jsonl — per-URL extraction log (atomic dedupe for --resume)session.json — pipeline stage, captured CLI opts, per-entity progress counters, and adapter pagination cursorsmedia-stubs.json — per-asset download status so permanently-broken URLs stop retrying across resume runsproducts.csv — WooCommerce-compatible product CSV (if the site has e-commerce)products.jsonl — raw product data streamed during extraction
Additional documentation
Related
respira-press