AIO-Osint

AIO-Osint

All in one Osint tools

Category
访问服务器

README

🔍 OSINT Tools MCP Server

MCP Server MIT License Python OSINT

A comprehensive MCP server that exposes multiple OSINT tools to AI assistants like Claude. This server allows AI to perform sophisticated reconnaissance and information gathering tasks using industry-standard OSINT tools.

🛠️ Available Tools

🔍 Sherlock - Username Search

Search for usernames across 399+ social media platforms and websites. Perfect for digital footprint analysis.

  • Input: Username
  • Output: List of platforms where username exists

📧 Holehe - Email Verification

Check if an email is registered on 120+ platforms. Lightning fast and accurate.

  • Input: Email address
  • Output: Platforms where email is registered

🕷️ SpiderFoot - Comprehensive OSINT

The Swiss Army knife of OSINT. Performs deep reconnaissance with automatic target type detection.

  • Input: IP, domain, email, phone, username, person name, Bitcoin address, or network block
  • Output: Comprehensive intelligence report
  • ⚠️ Note: SpiderFoot can take 5-30 minutes to complete a full scan. Be patient!

🔎 GHunt - Google Account Intel

Extract information from Google accounts using email or Google ID.

  • Input: Email or Google ID
  • Output: Google account details and associated information

🌐 Maigret - Advanced Username Search

Search across 3000+ sites with false positive detection and detailed analysis.

  • Input: Username
  • Output: Detailed report with confidence scores

🌾 TheHarvester - Domain Intelligence

Gather emails, subdomains, hosts, employee names, and more from public sources.

  • Input: Domain or company name
  • Output: Comprehensive domain intelligence

🐦 Blackbird - Fast Username OSINT

Lightning-fast searches across 581 sites for username reconnaissance.

  • Input: Username
  • Output: Quick profile discovery results

🚀 Installation

MCP Server Setup

  1. Clone this repository:
git clone https://github.com/frishtik/osint-tools-mcp-server.git
cd osint-tools-mcp-server
  1. Install dependencies:
pip install -r requirements.txt

This will automatically install Sherlock, Holehe, Maigret, and TheHarvester.

  1. Configure Claude Desktop:

Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "osint-tools": {
      "command": "python",
      "args": ["/path/to/osint-tools-mcp-server/src/osint_tools_mcp_server.py"],
      "env": {
        "PYTHONUNBUFFERED": "1"
      }
    }
  }
}
  1. Restart Claude Desktop to load the new MCP server.

Prerequisites for Additional Tools

Some tools require manual installation due to their complexity:

SpiderFoot

git clone https://github.com/smicallef/spiderfoot.git /opt/spiderfoot
cd /opt/spiderfoot
pip install -r requirements.txt

GHunt

git clone https://github.com/mxrch/GHunt.git /opt/ghunt
cd /opt/ghunt
pip install -r requirements.txt

Blackbird

git clone https://github.com/p1ngul1n0/blackbird.git /opt/blackbird
cd /opt/blackbird
pip install -r requirements.txt

🎮 Usage Tips

Getting Started

Working with AI for OSINT is a bit of an art form. Here's how to get the best results:

Start Simple with Holehe

I recommend starting with the Holehe tool - it's fast, reliable, and gives you immediate results:

"Check if john.doe@example.com is registered on any platforms"

Level Up to Username Searches

Once you're comfortable, try username searches with Sherlock or Maigret:

"Search for the username 'johndoe123' across social media platforms"

Complex Orchestrations

Here's where it gets interesting. You can chain tools together:

"I found an email address contact@suspicious-site.com. Can you:
1. Check what platforms it's registered on
2. Extract the domain and search for subdomains and other emails
3. Search for any usernames associated with this domain"

Let the AI Be Smart

Sometimes the best approach is to give Claude context and let it decide:

"I'm investigating the digital footprint of username 'hackerman2024'. 
Use your judgment to gather as much information as possible."

Pro Tips 🎯

  1. Be Patient with SpiderFoot: It's incredibly thorough but can take up to 30 minutes for a full scan. Start it and grab a coffee!

  2. Parallel Processing: Claude can run multiple tools simultaneously. Don't hesitate to ask for parallel searches:

    "Search for 'johndoe' on both Sherlock and Maigret at the same time"
    
  3. Know When to Hold the Leash:

    • For specific investigations: Be explicit about which tools to use
    • For exploratory research: Let Claude choose the tools
    • For time-sensitive tasks: Avoid SpiderFoot, stick to faster tools
  4. Cross-Reference Results: Different tools have different databases. Maigret might find accounts that Sherlock misses and vice versa.

  5. Email First, Username Second: If you have an email, start there - it's usually more unique than usernames.

⚖️ Ethical Usage & Legal Compliance

🚨 IMPORTANT: This tool is for legitimate security research and OSINT investigations only.

You MUST:

  • ✅ Only gather publicly available information
  • ✅ Respect privacy laws in your jurisdiction (GDPR, CCPA, etc.)
  • ✅ Follow platforms' Terms of Service
  • ✅ Use findings responsibly and ethically
  • ✅ Obtain proper authorization for any professional investigations

You MUST NOT:

  • ❌ Use this for stalking, harassment, or any malicious purpose
  • ❌ Violate any local, state, or federal laws
  • ❌ Access private or protected information
  • ❌ Use findings to harm individuals or organizations

🔧 Troubleshooting

Common Issues

Tools not found: Make sure all OSINT tools are installed and in your PATH:

which sherlock holehe maigret theharvester

SpiderFoot errors: Ensure SpiderFoot is installed in /opt/spiderfoot or update the path in the code.

Timeout issues: Some tools may timeout on slow connections. Try increasing the timeout parameter:

"Search for username with a 30 second timeout"

Rate limiting: Some platforms rate-limit searches. If you're getting blocked, wait a bit and try again.

🏗️ Architecture

This MCP server uses Python's asyncio for non-blocking tool execution. Each tool runs in a subprocess, allowing for parallel execution and proper timeout handling.

Claude Desktop <-> MCP Protocol <-> OSINT MCP Server <-> OSINT Tools

🤝 Contributing

Found a bug? Want to add a new tool? Contributions are welcome!

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/NewOSINTTool)
  3. Commit your changes (git commit -m 'Add NewOSINTTool support')
  4. Push to the branch (git push origin feature/NewOSINTTool)
  5. Open a Pull Request

📚 Acknowledgments

Special thanks to these awesome projects:

  • mcp-maigret - Inspiration for MCP implementation and README structure. Go give them a ⭐!
  • Model Context Protocol - The protocol making all this possible
  • All the incredible OSINT tool maintainers

📜 License

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

⚠️ Disclaimer

This tool is provided for educational and legitimate security research purposes only. The authors are not responsible for any misuse or damage caused by this program. Use at your own risk and always ensure you have proper authorization before conducting any investigations.


Remember: With great power comes great responsibility. Use these tools wisely and ethically! 🦸‍♂️

Built with ❤️ for the OSINT community

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选