ai-bookmark-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| readB | Parse a Netscape bookmark HTML file and return a concise summary of bookmarks and folders. |
| searchC | Search bookmarks by title, URL, domain, or folder path. |
| classifyB | Classify a URL/title into the bookmark taxonomy. |
| mergeB | Merge multiple bookmark HTML files. Deduplicates, classifies, renders folder SVG icons, and groups leaf folders by domain. |
| exportC | Export a bookmark file as classified HTML, JSON, CSV, or Markdown. |
| statsC | Get bookmark count, folder count, and top-level distribution for a bookmark file. |
| index_bookmarksC | Index bookmark metadata/content into a local SQLite FTS5 database. Offline mode is deterministic and network-free by default. |
| get_index_statusC | Return content index status for the SQLite bookmark database. |
| search_bookmarks_fulltextB | Search indexed bookmark page content using SQLite FTS5, with optional folder/domain filters. |
| get_bookmark_contentC | Return indexed content for a bookmark URL. |
| get_bookmark_content_rangeC | Return indexed content for a page range. Useful for PDF/page-aware sources when page offsets are available. |
| check_browser_connectionC | Check whether Chrome/Chromium is available through the Chrome DevTools Protocol remote debugging port. |
| open_in_browserB | Open a URL in Chrome via CDP, optionally extract visible DOM text and/or capture a screenshot. Tabs close by default. |
| extract_contentB | Open a URL in Chrome via CDP, extract visible page text and basic page counts, then close the tab. |
| navigate_and_readC | Alias for extract_content: navigate to a URL, extract visible page text, and close the tab. |
| read_bookmarksD | Alias for read. |
| search_bookmarksD | Alias for search. |
| get_treeC | Return the folder tree structure. |
| get_statsD | Alias for stats. |
| export_bookmarksD | Alias for export. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 20 tools
Multiple aliases (e.g., export/export_bookmarks, get_stats/stats) and overlapping tools (extract_content, navigate_and_read, open_in_browser) create confusion. Agents may struggle to select the correct tool.
Inconsistent naming: some tools use verb_noun (check_browser_connection, get_bookmark_content) while others use single verbs (classify, merge). Aliases further break patterns.
20 tools is borderline high for a bookmark server. Many are aliases, inflating the count. Core functionality could be served with fewer tools.
Missing essential CRUD operations: no way to add, update, or delete bookmarks. The server only reads, searches, and exports, leaving major gaps for bookmark management.