Skip to main content
Glama
bookmarks-mcp

bookmarks-mcp

bookmarks-mcp

Your bookmarks, wherever they live, readable by your AI.

Everyone saves. Browsers, read-later apps, that Pocket export from 2023 — capture is a solved problem. Processing is not: the average bookmark is saved once and never touched again. AI assistants are the first thing that can actually process a pile like that — summarize, triage, turn it into a to-do list — but they can't see it.

This is a local, read-only MCP server that fixes the "can't see it" part.

One command in your MCP client config. Zero accounts. Nothing is ever sent to us.

Sources

Source

How

Notes

Chrome, Edge, Brave, Arc, Vivaldi, Chromium

reads each profile's local Bookmarks file

every profile auto-detected

Safari (macOS)

reads ~/Library/Safari/Bookmarks.plist

includes your Reading List; no extension can do this — Safari's extension API has no bookmarks surface

Firefox

reads places.sqlite per profile

needs Node ≥ 22.5 (built-in sqlite); degrades gracefully below

Export files

Pocket CSV, Instapaper CSV, Raindrop CSV, browser HTML, URL lists

via parse-bookmarks

Phone bookmarks: reachable once they sync to your desktop (iCloud → Safari on Mac, Chrome sync → desktop profile). There is no way for any third-party tool to read Safari bookmarks directly on iOS.

Related MCP server: ai-bookmark-mcp

Install

No account, no API key, no configuration — the server works the moment it's installed.

Claude Code:

claude mcp add -s user bookmarks -- npx -y bookmarks-mcp

Use -s user. The scope defaults to local, which only registers the server for the directory you ran the command in. Your bookmarks aren't tied to one project, so register it account-wide.

Claude Desktop / Cursor / any MCP client (mcpServers JSON):

{
  "mcpServers": {
    "bookmarks": {
      "command": "npx",
      "args": ["-y", "bookmarks-mcp"]
    }
  }
}

To run from source instead (for development), clone this repo next to its dependency parse-bookmarks (the two directories must be siblings), run npm install in bookmarks-mcp, and point your client at node /absolute/path/to/bookmarks-mcp/src/index.js.

macOS + Safari: the app hosting the server (Claude Desktop, your terminal) needs Full Disk Access (System Settings → Privacy & Security), because ~/Library/Safari is protected. Chromium browsers and Firefox need nothing.

Tools

Tool

What it does

list_sources

every bookmark source found on this machine

list_bookmarks

list, with folder filter + pagination

search_bookmarks

search titles / URLs / folders / tags

recent_bookmarks

"what did I save this week?"

bookmark_stats

the state of the pile: counts, age distribution, top domains

parse_export_file

parse a Pocket/Instapaper/Raindrop/HTML export from disk

export_bookmarks

everything out as Markdown, CSV, JSON, or importable browser HTML

fetch_page_preview

a few-hundred-token preview of a page (title, description, headings, excerpt) instead of the raw HTML — for when title/URL alone can't be triaged

Turn the pile into a to-do list

The reason this exists. Ask your assistant:

Look at my bookmark stats, then help me triage: which of these become deep reads, which are tools to try, which feed a project I'm working on, and which should I finally let go? Give me a checklist for this week.

Or use the built-in triage_bookmarks prompt, which walks through exactly that — including asking you to define what your saves usually become, so the lanes are yours, not ours.

Guarantees

  • Read-only. This server never writes to a browser file. There is no delete tool. Your bookmarks cannot be harmed.

  • Zero phone-home. No telemetry, no accounts, and not a single byte sent to us. The server talks to exactly two places: your local bookmark files, and — only when you ask it to preview a page — the bookmarked site itself, directly from your machine.

  • Clean output. Tool results are data. No ads, no upsells, ever.

Design boundaries

These are deliberate, not gaps waiting to be filled. PRs that cross them will be declined:

  • Preview-level extraction only. fetch_page_preview answers "is this worth my time" — it is not a reader mode and never will be a full-fidelity content extractor.

  • Public web pages only. No proxies, no login walls, no special-casing for X/YouTube/WeChat/etc. If a page needs auth to read, this tool isn't the way in.

  • On-demand only. Nothing fetches in the background, ever. Every network call is a direct response to a tool call you made.

Roadmap

  • Cloud sources behind user-supplied tokens (Raindrop, Readwise, …) — one adapter per service. PRs welcome; an adapter is a single well-defined file.

  • Services that already ship their own MCP server don't need us — run both servers and your assistant sees everything. We only cover the places that have no other bridge.

Who makes this

Built by the team behind Burn 451, a read-later app. This server is deliberately neutral: it reads your bookmarks for whatever assistant and whatever workflow you choose, and it never writes to them.

License

MIT

Available Tools

8 tools
bookmark_statsBookmark statisticsA

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.

Inputs: source.

export_bookmarksExport bookmarksA

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

Inputs: format (required), source.

fetch_page_previewFetch a clean page previewA

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.

Inputs: url (required), refresh.

list_bookmarksList bookmarksB

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

Inputs: limit, folder, offset, source.

list_sourcesList bookmark sourcesA

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.

Inputs: no named parameters.

parse_export_fileParse a bookmark export fileA

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.

Inputs: path (required), format.

recent_bookmarksRecently added bookmarksA

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

Inputs: days, limit, source.

search_bookmarksSearch bookmarksA

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

Inputs: query (required), limit, source.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: listing, searching, recent, stats, parsing, exporting, previewing, and source detection. No two tools overlap in functionality, and the descriptions reinforce their unique roles.

    Naming Consistency4/5

    Most tools follow a consistent verb_noun snake_case pattern (list_bookmarks, search_bookmarks, export_bookmarks). Two tools deviate slightly (recent_bookmarks, bookmark_stats) but remain readable and stylistically consistent.

    Tool Count5/5

    Eight tools is a well-scoped count for a bookmark management server. Each tool addresses a distinct aspect of bookmark interaction without redundancy or bloat.

    Completeness2/5

    The tool set is heavily read-oriented with export and parsing utilities, but lacks write operations such as add, update, or delete bookmarks. Agents can identify dead links via fetch_page_preview but have no way to retire them, representing a significant functional gap.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Fully local, privacy-first MCP server that turns exported X/Twitter bookmarks into a searchable, enriched knowledge base for Claude Desktop and Claude Code.
      3
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Read-only local-first MCP server enabling AI assistants to semantically search private Markdown, PDF, and Tika-backed knowledge bases without data upload.
      44
      MIT