Sherlock MCP Server

Sherlock MCP Server

Enables username enumeration across 400+ social media platforms using the Sherlock OSINT tool. Perfect for open-source intelligence gathering, cybersecurity research, and investigating social media presence through AI assistants.

Category
访问服务器

README

Sherlock MCP Server

GitHub stars GitHub issues Python Version License: MIT Docker

FastMCP server integration for the Sherlock OSINT tool – Seamlessly search social media accounts across 400+ platforms using the Model Context Protocol. Perfect for OSINT researchers, cybersecurity professionals, and AI assistants performing username enumeration and open-source intelligence gathering.

Mission

This project is built with a commitment to finding truth and countering propaganda through ethical open-source intelligence. In an era of misinformation and digital manipulation, we believe in empowering investigators, journalists, and truth-seekers with transparent, verifiable tools for social media reconnaissance.

Our mission is to:

  • Promote Truthful Investigation: Provide reliable tools for fact-checking and source verification
  • Counter Propaganda: Enable systematic analysis of online narratives and account authenticity
  • Maintain Ethical Standards: Ensure all usage aligns with privacy rights and responsible disclosure
  • Foster Transparency: Open-source development for community scrutiny and improvement

Read our full Mission Statement for detailed principles and applications.

Features

  • Username Search: Find social media profiles associated with a username
  • Structured Output: Returns formatted results with site names, URLs, and existence status
  • Error Handling: Graceful handling of missing dependencies, timeouts, and failures
  • Ethical Use: Designed for responsible OSINT investigations
  • MCP Integration: Native support for Model Context Protocol in AI workflows

Demo

Experience the power of OSINT username searching with this MCP server. Connect to your favorite MCP-compatible AI assistant and query social media presence instantly.

Placeholder for demo GIF or screenshot – coming soon!

Prerequisites

  • Python 3.13+
  • Sherlock CLI tool installed: pipx install sherlock-project

Docker Setup

For containerized deployment using the official Sherlock Docker image:

  1. Build the Docker image:

    docker build -t sherlock-mcp .
    
  2. Run the container:

    docker run -it sherlock-mcp
    

This starts the MCP server inside the container. Connect MCP clients via stdio pipes or configure HTTP transport for remote access.

Installation

  1. Clone this repository:

    git clone <repo-url>
    cd sherlock-mcp
    
  2. Install dependencies:

    pip install -e .
    
  3. Ensure Sherlock is installed:

    pipx install sherlock-project
    

Usage

Running the Server

python main.py

This starts the MCP server with stdio transport, ready for MCP clients.

Example MCP Client Usage

When connected to an MCP-compatible client (e.g., Claude Desktop), use the search_username tool:

Tool: search_username
Arguments: {"username": "exampleuser"}

Response:

{
  "found": [
    {"site": "github", "url": "https://github.com/exampleuser", "exists": true},
    {"site": "twitter", "url": "https://twitter.com/exampleuser", "exists": true}
  ],
  "total_found": 2,
  "error": null
}

Tool Reference

search_username(username: str)

Searches for social media accounts associated with the given username.

Parameters:

  • username (str): The username to search for

Returns:

  • found (list): Array of found profiles with site, URL, and exists status
  • total_found (int): Number of profiles found
  • error (str): Error message if any (null on success)

Contributing

We welcome contributions to enhance this OSINT MCP server! Whether it's bug fixes, new features, or documentation improvements, your input helps the cybersecurity and AI communities.

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

Please read our Contributing Guidelines for more details.

Ethical Considerations

This tool is designed for truth-seeking and countering propaganda, but with great power comes great responsibility. Always use ethically and legally.

General Guidelines

  • Use only for legitimate OSINT purposes
  • Respect platform terms of service
  • Be aware of privacy implications
  • Consider rate limiting to avoid overwhelming services

Countering Propaganda Best Practices

  • Cross-Reference Sources: Verify account authenticity across multiple platforms
  • Check Creation Dates: New accounts may indicate coordinated campaigns
  • Analyze Patterns: Look for coordinated posting behaviors or similar content
  • Respect Privacy: Focus on public information and avoid doxxing
  • Fact-Check Results: Use additional verification tools for claims
  • Document Methodology: Maintain transparency in investigative processes
  • Avoid Harm: Do not use findings to harass or intimidate individuals

Responsible Usage

  • Obtain proper authorization for investigations
  • Comply with local laws and regulations
  • Use findings to promote truth and accountability
  • Share results responsibly to avoid contributing to misinformation

Troubleshooting

  • Sherlock not found: Install with pipx install sherlock-project
  • Timeout errors: Increase timeout in code or use smaller username sets
  • No results: Username may not exist on searched platforms

License

MIT License

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