Savage Scraper

Scrapes rendered pages into simplified LLM-friendly HTML for clipboard, local preview, or optional MCP workflows.

Savage Scraper works out of the box with no setup required! Manual mode Open any normal web page and click the Savage Scraper toolbar action once. Savage Scraper captures the rendered active page, simplifies its useful structure, and copies the result directly to the local clipboard. Manual mode is the default. It does not require configuring Savage MCP, granting broad website access, or setting up any external service. Savage Scraper keeps useful semantic content such as headings, lists, tables, forms, dialogs, links, open Shadow DOM, readable same-origin iframe content, and supported xterm.js terminal output. Empty table cells are preserved so table structure stays aligned. Password values and hidden input controls are excluded. After a capture, PREVIEW opens the exact generated result in a local extension tab. The captured text and semantic content are preserved while custom reader styling is applied for readability. Original page CSS, scripts, live frames, and remote resources are not loaded automatically. Optional MCP mode MCP mode is disabled by default. If the user installs the separate local Savage MCP server and explicitly enables MCP website access, an MCP client can read selected HTTP/HTTPS pages through the user's existing Chrome profile and browser session. The local Savage MCP configuration controls access through allowed_hosts and optional allowed_paths restrictions. The bridge connects only to Savage MCP on 127.0.0.1. The MCP browser surface is intentionally limited to opening allowed URLs, scraping one dedicated agent tab, and reporting status. It does not expose generic clicking, typing, form submission, arbitrary JavaScript execution, or unrestricted browser control. MCP captures use the same saved Include hidden content and Pretty-format HTML settings as manual captures. Manual captures and previews are processed locally. MCP results are returned only to the user's locally running Savage MCP process. Savage Scraper contains no analytics, advertising, telemetry, or remotely hosted executable code and does not send scraped page content to the developer. Open source: Savage Scraper: https://github.com/dominikduda/savage_scraper Savage MCP: https://github.com/dominikduda/savage_mcp Privacy policy: https://github.com/dominikduda/savage_scraper/blob/main/PRIVACY.md