Detect every bookmark source on this machine: Chromium-family profiles (Chrome, Edge, Brave, Arc, Vivaldi), Firefox profiles, and Safari (incl. Reading List). Returns ids usable as the source argument of other tools.

List bookmarks from detected browsers. Supports folder filter and pagination.

Case-insensitive search across bookmark titles, URLs, folders, and tags in every detected browser.

Bookmarks added in the last N days, newest first. Useful for what did I save this week?.

The state of the pile: total count, per-source counts, age distribution (how much has sat untouched for years), and top domains. A good first call before triaging.

Parse a bookmark export file from disk into clean JSON. Auto-detects: browser bookmark HTML (Netscape), Pocket CSV, Instapaper CSV, Raindrop CSV, or a plain URL list.

Export bookmarks from detected browsers as markdown, csv, json, or importable browser HTML (Netscape format). Returns the file content; save it wherever you like.

Fetch a bookmarked URL and return a short, structured preview (title, description, headings, an opening excerpt, word count) instead of the raw page — a few hundred tokens instead of tens of thousands. Use this only when a title/URL alone isn't enough to triage a bookmark: dead links come back as dead or unreachable so you can retire them without guessing, rather than raw HTML. Results are cached locally per URL; pass refresh:true to bypass the cache.