Skip to main content
Glama

list_safari_bookmarks

Retrieve Safari bookmarks to enable AI agents to access saved websites and favorites on macOS.

Instructions

List Safari bookmarks

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • server.js:82-86 (registration)
    Tool registration in a loop that registers all tools including list_safari_bookmarks. Each tool is registered with the McpServer using a stub handler that returns an inspection message.
    for (const [name, desc] of TOOLS) {
      server.tool(name, desc, {}, async () => ({
        content: [{ type: "text", text: "This is an inspection stub. Install Pilot MCP on macOS: npx -y local-mcp@latest setup" }],
      }));
    }
  • TOOLS array containing the tool name and description definitions. list_safari_bookmarks is defined at line 73 with description "List Safari bookmarks".
    const TOOLS = [
      ["list_emails", "List emails from Mail.app inbox with optional filters"],
      ["read_email", "Read full email content by ID"],
      ["search_emails", "Search emails by keyword, sender, or date range"],
      ["send_email", "Compose and send a new email"],
      ["reply_email", "Reply to an existing email"],
      ["move_email", "Move email to a different mailbox"],
      ["save_attachment", "Save email attachment to disk"],
      ["list_calendar_names", "List available calendars"],
      ["list_calendar_events", "List calendar events for a date range"],
      ["create_calendar_event", "Create a new calendar event"],
      ["delete_calendar_event", "Delete a calendar event with preview"],
      ["list_reminders", "List reminders from a specific list"],
      ["list_reminder_lists", "List all reminder lists"],
      ["create_reminder", "Create a new reminder"],
      ["complete_reminder", "Mark a reminder as complete"],
      ["list_contacts", "List contacts from the address book"],
      ["search_contacts", "Search contacts by name, email, or phone"],
      ["get_contact", "Get full contact details by name"],
      ["list_notes", "List notes from Apple Notes"],
      ["read_note", "Read full note content"],
      ["create_note", "Create a new note in Apple Notes"],
      ["search_notes", "Search notes by keyword"],
      ["list_message_chats", "List recent iMessage conversations"],
      ["read_messages", "Read messages from a conversation"],
      ["search_messages", "Search iMessages by keyword"],
      ["list_omnifocus_tasks", "List tasks from OmniFocus"],
      ["list_omnifocus_projects", "List OmniFocus projects"],
      ["create_omnifocus_task", "Create a new task in OmniFocus"],
      ["complete_omnifocus_task", "Mark an OmniFocus task complete"],
      ["search_omnifocus_tasks", "Search OmniFocus tasks"],
      ["list_omnifocus_tags", "List OmniFocus tags"],
      ["outlook_list_emails", "List emails from Microsoft Outlook"],
      ["outlook_read_email", "Read an Outlook email"],
      ["outlook_search_emails", "Search Outlook emails"],
      ["outlook_send_email", "Send email via Outlook"],
      ["outlook_list_events", "List Outlook calendar events"],
      ["outlook_create_event", "Create Outlook calendar event"],
      ["onedrive_list_files", "List files and folders in OneDrive"],
      ["onedrive_read_file", "Read file content from OneDrive"],
      ["onedrive_search_files", "Search files in OneDrive"],
      ["onedrive_write_file", "Write or upload file to OneDrive"],
      ["onedrive_delete_file", "Delete file from OneDrive"],
      ["onedrive_move_file", "Move or rename file in OneDrive"],
      ["finder_list", "List files in a Finder directory"],
      ["finder_search", "Search files using Spotlight"],
      ["pdf_read", "Read text content from a PDF file"],
      ["word_read", "Read content from a Word document"],
      ["word_create", "Create a new Word document"],
      ["word_append", "Append content to a Word document"],
      ["excel_read", "Read data from an Excel spreadsheet"],
      ["excel_create", "Create a new Excel spreadsheet"],
      ["excel_write_cell", "Write data to Excel cells"],
      ["ppt_read", "Read content from a PowerPoint file"],
      ["ppt_create", "Create a new PowerPoint presentation"],
      ["teams_list_chats", "List Microsoft Teams chat conversations"],
      ["teams_read_chat_messages", "Read messages from a Teams chat"],
      ["teams_list_teams", "List Teams and their channels"],
      ["teams_list_channels", "List channels in a Teams team"],
      ["teams_read_channel_messages", "Read messages from a Teams channel"],
      ["list_safari_bookmarks", "List Safari bookmarks"],
      ["list_accounts", "List configured email and calendar accounts"],
      ["create_email_folder", "Create a new email folder/mailbox"],
      ["diagnose", "Run diagnostic checks on all connected services"],
      ["report_bug", "Report a bug or issue to the development team"],
      ["request_feature", "Request a new feature"],
      ["request_integration", "Request integration with an unsupported app"],
    ];
  • server.js:82-86 (handler)
    Stub handler implementation for list_safari_bookmarks. Returns a placeholder message indicating this is an inspection stub and the real server is a native macOS binary.
    for (const [name, desc] of TOOLS) {
      server.tool(name, desc, {}, async () => ({
        content: [{ type: "text", text: "This is an inspection stub. Install Pilot MCP on macOS: npx -y local-mcp@latest setup" }],
      }));
    }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states nothing about the return format (folder hierarchy vs flat list), scope (all bookmarks vs favorites bar), or any system permissions required to access Safari data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise at three words with no filler. However, it borders on under-specification given the lack of output schema. Every word earns its place, though additional content would improve utility.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description fails to document the return structure (e.g., whether it returns folder hierarchies, URLs, titles, or IDs). For a tool accessing browser data, documentation of the response format is essential and missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters with 100% coverage. Per the scoring guidelines, zero-parameter tools receive a baseline score of 4, as there are no parameter semantics to describe.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'List Safari bookmarks' is a tautology that restates the tool name. While it clearly identifies the resource (Safari bookmarks) and action (list), it fails to add specificity or distinguish from sibling list_* tools beyond the resource name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance provided on when to use this tool versus alternatives like searching bookmarks or accessing other browser data. No prerequisites or conditions mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lanchuske/local-mcp-releases'

If you have feedback or need assistance with the MCP directory API, please join our Discord server