MCP Bookmarks
A VSCode extension that provides MCP tools for AI assistants to programmatically create, manage, and annotate code bookmarks. It enables AI-driven and manual organization of codebase architecture, flows, and key components through hierarchical bookmarks and groups.
README
MCP Bookmarks
Code bookmarks extension for VSCode with MCP (Model Context Protocol) integration, allowing AI assistants to annotate and explain your codebase.
Features
- MCP Integration: Provides MCP tools for AI assistants (Claude Code, Gemini, etc.) to create and manage bookmarks programmatically
- AI Assistant Support: AI can analyze your code and create organized bookmarks to explain architecture, flows, and key components
- Manual Management: Full support for creating, editing, and organizing bookmarks without AI
- Hierarchical Bookmarks: Create parent-child bookmark relationships to represent call chains and code flows
- Grouped Organization: Bookmarks are organized into groups by topic, feature, or analysis session
- Category System: 4 built-in categories (entry-point, core-logic, issue, note) for clear organization
- Markdown Link Support: Cross-reference code locations with clickable links in bookmark descriptions
- Rich Sidebar: Interactive webview with tree/nested view modes, search, and filtering
- Editor Integration: Inline gutter icons, hover previews, and CodeLens support
- Quick Navigation: Jump to bookmarked locations, navigate between bookmarks with keyboard shortcuts
- Export & Share: Export bookmarks to Markdown, store in
.vscode/mcp-bookmarks.jsonfor version control
Installation
Method 1: Install from VSIX (Recommended)
- Download the latest
.vsixfile from Releases - In VSCode, open Command Palette (
Cmd+Shift+PorCtrl+Shift+P) - Run
Extensions: Install from VSIX... - Select the downloaded
.vsixfile
Method 2: Install from Source
# Clone repository
git clone https://github.com/linonon/mcp-bookmarks.git
cd mcp-bookmarks
# Install dependencies and build
npm install
npm run compile
# Package as VSIX
npm run package
# Install the generated .vsix file
code --install-extension mcp-bookmarks-*.vsix
MCP Configuration
After installing the extension, configure MCP integration for your AI tool.
Quick Setup
- Open Command Palette (
Cmd+Shift+PorCtrl+Shift+P) - Run
MCP Bookmarks: Copy MCP Setup Command - Select your AI tool (Claude Code / Gemini / Codex / VSCode)
- The command will be copied to your clipboard
For Claude Code Users
Run this command in your terminal (generated by the extension):
claude mcp add -s user mcp-bookmarks -- node "~/.vscode/mcp-bookmarks-launcher.js"
Or manually configure in .claude/mcp.json:
{
"mcpServers": {
"mcp-bookmarks": {
"command": "node",
"args": ["/Users/YOUR_USERNAME/.vscode/mcp-bookmarks-launcher.js"],
"description": "MCP Bookmarks - Code annotation and navigation"
}
}
}
For Gemini Users
Run this command in your terminal (generated by the extension):
gemini mcp add -s user mcp-bookmarks node "~/.vscode/mcp-bookmarks-launcher.js"
For VSCode MCP Extension Users
- Press
Cmd+P(Mac) orCtrl+P(Windows) - Type
MCP: Open User Configuration - Add the following configuration:
{
"mcpServers": {
"mcp-bookmarks": {
"type": "stdio",
"command": "node",
"args": ["/Users/YOUR_USERNAME/.vscode/mcp-bookmarks-launcher.js"]
}
}
}
For Codex Users
Paste this snippet into ~/.codex/config.toml:
[mcp_servers."mcp-bookmarks"]
command = "node"
args = ["/Users/YOUR_USERNAME/.vscode/mcp-bookmarks-launcher.js"]
Note: Use the Copy MCP Setup Command to get the correct path automatically!
Usage
Complete Setup Flow
Step 1: Install Extension
# Download .vsix from GitHub Releases
# Then in VSCode Command Palette:
Extensions: Install from VSIX...
Step 2: Configure MCP (Automatic)
# In VSCode Command Palette:
MCP Bookmarks: Copy MCP Setup Command
# Select your AI tool (Claude Code / Gemini / Codex / VSCode)
# Copy the generated command
# For Claude Code, run in terminal:
claude mcp add -s user mcp-bookmarks -- node "~/.vscode/mcp-bookmarks-launcher.js"
# For Gemini, run in terminal:
gemini mcp add -s user mcp-bookmarks node "~/.vscode/mcp-bookmarks-launcher.js"
# For VSCode MCP, paste the path into User Configuration
Step 3: Start Using
Now your AI assistant can create bookmarks in your codebase!
Available MCP Tools
create_group- Create a bookmark groupadd_bookmark- Add a bookmark to a groupbatch_add_bookmarks- Add multiple bookmarks at oncelist_groups- List all groupslist_bookmarks- List bookmarks with filtersget_group- Get group details with all bookmarksget_bookmark- Get single bookmark detailsupdate_group- Update group infoupdate_bookmark- Update bookmark propertiesremove_group- Delete a group and its bookmarksremove_bookmark- Delete a single bookmarkclear_all_bookmarks- Clear all data (requires confirmation)
For Users
Commands:
MCP Bookmarks: Refresh- Refresh the bookmark treeMCP Bookmarks: Add Bookmark Here- Manually add a bookmark at cursorMCP Bookmarks: Create Group- Create a new bookmark groupMCP Bookmarks: Edit Group- Edit group title and descriptionMCP Bookmarks: Rename Group- Quick rename a group (F2)MCP Bookmarks: Delete Group- Delete a group and its bookmarksMCP Bookmarks: Edit Bookmark- Edit bookmark propertiesMCP Bookmarks: Delete Bookmark- Delete a bookmarkMCP Bookmarks: Move to Group...- Move bookmark to another groupMCP Bookmarks: Move Bookmark Up/Down- Reorder bookmarks within groupMCP Bookmarks: Search Bookmarks- Search through all bookmarksMCP Bookmarks: Export as Markdown- Export bookmarks to markdownMCP Bookmarks: Toggle View Mode- Switch between group/file viewMCP Bookmarks: Expand All- Expand all tree nodesMCP Bookmarks: Collapse All- Collapse all tree nodes
Configuration
| Setting | Default | Description |
|---|---|---|
mcpBookmarks.mcpPort |
3333 | MCP Server port |
mcpBookmarks.showInlineDecorations |
true | Show bookmark icons in gutter |
mcpBookmarks.viewMode |
"group" | View mode: "group" or "file" |
mcpBookmarks.quickAddMode |
"simple" | Quick add mode: "full" (all options) or "simple" (title only) |
mcpBookmarks.defaultCategory |
"explanation" | Default category for new bookmarks |
mcpBookmarks.confirmBeforeDelete |
true | Show confirmation before deleting |
Data Storage
Bookmarks are stored in .vscode/mcp-bookmarks.json within your workspace. This file can be committed to version control to share bookmarks with your team.
Development
# Install dependencies
npm install
# Watch mode (auto-recompile)
npm run watch
# Compile once
npm run compile
# Package extension
npm run package
# Lint
npm run lint
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.