Chrome History & Bookmarks MCP Server
Enables AI assistants to search and analyze Chrome browser history and bookmarks data locally, including keyword searches, date range filtering, recent browsing activity, and usage statistics across all platforms.
README
Chrome History & Bookmarks MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with tools to analyze Chrome browser history and bookmarks data.
Features
🔍 History Search - Search through Chrome browsing history by keywords, URLs, and date ranges
📊 History Statistics - Get insights about your browsing data including date ranges and visit counts
⏰ Recent Browsing - View recent browsing activity from the last 24 hours (configurable)
🔖 Bookmarks Access - Read and analyze Chrome bookmarks (coming soon)
📈 Browsing Patterns - Analyze browsing habits and patterns (coming soon)
📤 Data Export - Export history and bookmarks to various formats (coming soon)
Installation
-
Clone the repository:
git clone https://github.com/your-username/chrome-history-mcp-server.git cd chrome-history-mcp-server -
Install dependencies:
npm install -
Run the server:
node src/mcp-server.js
Usage with Claude Desktop
-
Configure Claude Desktop by editing your config file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
Windows:%APPDATA%/Claude/claude_desktop_config.json -
Add the MCP server configuration:
{ "mcpServers": { "chrome-history": { "command": "node", "args": ["/path/to/your/project/src/mcp-server.js"], "env": {} } } } -
Restart Claude Desktop and start using the tools!
Available Tools
search_history
Search through Chrome browsing history with optional date filtering.
Example usage:
"Search my browser history for 'github'"
"Find all YouTube videos I watched last week"
"Show me what I browsed between 2024-01-01 and 2024-01-31"
get_recent_browsing
Get browsing activity from recent hours with visit details and timestamps.
Example usage:
"Show me what I've been browsing in the last 24 hours"
"What websites did I visit in the last 6 hours?"
get_history_stats
Get statistics about your Chrome history database including date ranges and total entries.
Example usage:
"Show me my Chrome history statistics"
"What's the date range of my browsing history?"
How It Works
This MCP server:
- Locates Chrome - Automatically finds Chrome profile directory across platforms (macOS, Windows, Linux)
- Reads SQLite Database - Safely accesses Chrome's History database in read-only mode
- Provides Tools - Exposes browsing data through standardized MCP tools
- Cross-Platform - Works with Chrome, Chromium, and various Chrome profiles
Architecture
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Claude │ │ MCP Server │ │ Chrome │
│ Desktop │◄──►│ (This Project) │◄──►│ Browser │
│ (AI Client) │ │ │ │ SQLite DB │
└─────────────────┘ └──────────────────┘ └─────────────────┘
Technical Details
- Language: JavaScript (ES modules)
- Protocol: Model Context Protocol (MCP)
- Database: SQLite3 (Chrome's History database)
- Platforms: macOS, Windows, Linux
- Chrome Support: Chrome, Chromium, multiple profiles
Security & Privacy
- Read-only access - Never modifies Chrome data
- Local processing - All data stays on your machine
- No network requests - Operates entirely offline
- Database safety - Uses SQLite read-only mode to prevent corruption
Requirements
- Node.js 16+ with ES modules support
- Chrome/Chromium installed and run at least once
- MCP-compatible client (like Claude Desktop)
Contributing
Contributions welcome! Please feel free to submit issues and pull requests.
License
MIT License - see LICENSE file for details.
Troubleshooting
"Chrome installation not found"
- Ensure Chrome is installed and has been run at least once
- Check if you're using a custom Chrome profile location
"Database query failed"
- Make sure Chrome is closed (database might be locked)
- Verify Chrome profile permissions
"No results for date range"
- Use
get_history_statsto check available date range - Ensure date format is YYYY-MM-DD
Future Features
- 🔖 Full bookmarks analysis and search
- 📊 Advanced browsing pattern analysis
- 📤 Export to JSON, CSV, HTML formats
- 🧹 Privacy-focused history cleaning tools
- 📈 Browsing time analytics and insights
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。