trackmcp
Back to directory
mixophrygian

browser_history_mcp

View on GitHub

A local MCP server Claude Desktop can use to analyze your browser history

5 stars PythonAI & Machine Learning Updated Sep 28, 2025

Documentation

Browser History MCP Server

Python
MCP
License
Status

A local Model Context Protocol (MCP) server that provides access to browser history data for comprehensive analysis and insights. Built using the official python MCP sdk, this tool can be added to Claude desktop in a few minutes using the Quick Start guide.

๐Ÿ“‹ Table of Contents

โœจ Features

  • ๐Ÿ” Multi-Browser Support: Query Firefox, Chrome, and (some versions of) Safari browser history
  • ๐Ÿ“Š Session Analysis: Group browsing sessions with intelligent time-based clustering
  • ๐Ÿท๏ธ Smart Categorization: Automatically categorize websites by type and purpose
  • ๐Ÿ“ˆ Domain Analytics: Analyze domain frequency and visit patterns
  • ๐ŸŽฏ Learning Insights: Identify learning patterns and educational content consumption
  • โšก Productivity Metrics: Calculate productivity scores and distraction analysis
  • ๐Ÿ”„ Real-time Access: Direct database access for immediate insights
  • ๐Ÿ›ก๏ธ Privacy-First: Local processing with no data transmission

๐Ÿš€ Quick Start

1. Install `uv` for dependency management:

bash
curl -LsSf https://astral.sh/uv/install.sh | sh
   uv sync

2. Test locally:

bash
uv run mcp dev server/main.py

3. Install for Claude Desktop (you will need to restart Claude Desktop afterwards):

bash
uv run mcp install server/main.py --name "Browser History MCP"

๐Ÿ“ฆ Detailed installation

Prerequisites

  • Python 3.12 or higher
  • Firefox, Chrome, or Safari browser
  • uv (recommended) or pip
bash
# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

# Clone and install
git clone https://github.com/yourusername/browser-mcp-server.git
cd browser-mcp-server
uv sync

Using pip

bash
git clone https://github.com/yourusername/browser-mcp-server.git
cd browser-mcp-server
pip install -e .

โš™๏ธ Configuration

The server automatically detects your browser profile directories:

OSFirefox PathChrome Path
macOS`~/Library/Application Support/Firefox/Profiles/[profile-id].default-release``~/Library/Application Support/Google/Chrome/Default`
Linux`~/.mozilla/firefox/[profile-id].default-release``~/.config/google-chrome/Default`
Windows`%APPDATA%\Mozilla\Firefox\Profiles\[profile-id].default-release``%LOCALAPPDATA%\Google\Chrome\User Data\Default`

Manual Configuration

If automatic detection fails, manually configure paths in `server/main.py`:

python
FIREFOX_PROFILE_DIR = "/path/to/your/firefox/profile"
CHROME_PROFILE_DIR = "/path/to/your/chrome/profile"

Development Mode

bash
uv run mcp dev server/main.py

Pro tip: Open the version of the local URL with the token pre-filled. Then hit "Connect"

Use with Claude Desktop

bash
uv run mcp install server/main.py --name "Browser History MCP"

๐Ÿ“š API Reference

Core Tools

ToolDescriptionUse Case
`health_check`Simple health check to test if the MCP server is workingInitial testing
`check_browser_status`Step 1: Check which browsers are available and which are lockedInitial setup and troubleshooting
`get_browser_history`Step 2: Get raw browser history data without analysis (fastest)Quick data retrieval
`analyze_browser_history`Step 3: Main analysis tool with options for quick_summary, basic, or comprehensive analysisFull productivity analysis
`search_browser_history`Search browser history for specific queriesTargeted research
`suggest_categories`Get uncategorized URLs for custom categorizationData organization
`diagnose_safari_support`Safari support and accessibility diagnosticsSafari-specific issues

Analysis Prompts

PromptPurposeOutput
`productivity_analysis`Comprehensive productivity assessmentProductivity metrics and recommendations
`learning_analysis`Deep learning pattern analysisLearning insights and progress tracking
`research_topic_extraction`Research topic extraction and summarizationResearch themes and focus areas
`generate_insights_report`Create personalized browsing insightsComprehensive activity and behavior report
`compare_time_periods`Compare browsing habits across timeTrend analysis and habit transformation metrics
`export_visualization`Generate data visualizationsInteractive charts and visual analytics

๐ŸŒ Browser Support

BrowserStatusRequirements
Firefoxโœ… Full SupportBrowser must be closed
Chromeโœ… Full SupportBrowser must be closed
Safari๐Ÿ”„ Limited SupportMostly older versions of Safari

Important: Browsers must be closed to access their history databases due to file locking mechanisms.

Troubleshooting

MCP Config

code
{
  "mcpServers": {
    "Browser History MCP": {
      "command": "/usr/local/bin/uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "[wherever-you-saved-the-repo]/browser-mcp-server/server/main.py"
      ]
    }
  }
}

๐Ÿ”’ Privacy & Security

Data Handling

  • Local Processing: All data processing occurs locally on your machine
  • No Data Transmission: No browser history data is sent to external servers (aside from whatever Claude desktop is doing)
  • Direct Database Access: Reads directly from browser SQLite databases
  • Temporary Caching: Optional local caching for performance

๐Ÿ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

Frequently asked questions

What is browser_history_mcp?

browser_history_mcp is A local MCP server Claude Desktop can use to analyze your browser history

How do I install browser_history_mcp?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is browser_history_mcp open source?

Yes โ€” it is hosted on GitHub at https://github.com/mixophrygian/browser_history_mcp and has 5 stars.

Related MCP tools

All-Hands-AIopenhands

๐Ÿ™Œ OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.

64,677 Python
agentartificial-intelligencechatgpt+6
mem0aimem0

Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.

42,646 Python
agentsaiai-agents+12
zhayujiechatgpt-on-wechat

ๅŸบไบŽๅคงๆจกๅž‹ๆญๅปบ็š„่Šๅคฉๆœบๅ™จไบบ๏ผŒๅŒๆ—ถๆ”ฏๆŒ ๅพฎไฟกๅ…ฌไผ—ๅทใ€ไผไธšๅพฎไฟกๅบ”็”จใ€้ฃžไนฆใ€้’‰้’‰ ็ญ‰ๆŽฅๅ…ฅ๏ผŒๅฏ้€‰ๆ‹ฉChatGPT/Claude/DeepSeek/ๆ–‡ๅฟƒไธ€่จ€/่ฎฏ้ฃžๆ˜Ÿ็ซ/้€šไน‰ๅƒ้—ฎ/ Gemini/GLM-4/Kimi/LinkAI๏ผŒ่ƒฝๅค„็†ๆ–‡ๆœฌใ€่ฏญ้Ÿณๅ’Œๅ›พ็‰‡๏ผŒ่ฎฟ้—ฎๆ“ไฝœ็ณป็ปŸๅ’Œไบ’่”็ฝ‘๏ผŒๆ”ฏๆŒๅŸบไบŽ่‡ชๆœ‰็Ÿฅ่ฏ†ๅบ“่ฟ›่กŒๅฎšๅˆถไผไธšๆ™บ่ƒฝๅฎขๆœใ€‚

39,573 Python
aiai-agentchatgpt+17
assafelovicgpt-researcher

An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations. Built for the Model Context Protocol to

24,026 Python
agentaiautomation+8
jlowinfastmcp

๐Ÿš€ The fast, Pythonic way to build MCP servers and clients Trusted by 19900+ developers. Trusted by 19900+ developers. Trusted by 19900+ developers.

19,927 Python
agentsfastmcpllms+6
1Panel-devmaxkb

๐Ÿ”ฅ MaxKB is an open-source platform for building enterprise-grade agents. MaxKB ๆ˜ฏๅผบๅคงๆ˜“็”จ็š„ๅผ€ๆบไผไธš็บงๆ™บ่ƒฝไฝ“ๅนณๅฐใ€‚ for the Model Context Protocol. Enhance AI assistants with po

19,062 Python
agentagentic-aichatbot+11

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP