Cover image
Try Now
2025-04-03

用于分析浏览器扩展安全性的模型上下文协议(MCP)服务器

3 years

Works with Finder

1

Github Watches

2

Github Forks

9

Github Stars

MIT License

Centered Image


SecureAnnex MCP Server

A Model Context Protocol (MCP) server for analyzing browser extension security. This server provides tools for querying, analyzing, and evaluating security aspects of browser extensions including vulnerability detection, signature checking, code review, and more.

Quick Setup

No manual Python environment setup is needed. This MCP server is designed to work with Claude Desktop, which automatically handles all dependencies using the uv package manager and the included pyproject.toml file.

To get started:

  1. Download or clone this repository
  2. Make sure the pyproject.toml file is in the project directory
  3. Configure Claude Desktop as shown below
  4. Optional: If Claude can't find the uv command, use the absolute path instead, You can find the absolute path by running which uv in your terminal.

Claude Desktop Configuration

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "secureannex": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/secure-annex-mcp",
        "run",
        "secure_annex_mcp"
      ],
      "env": {
        "SECUREANNEX_API_KEY": "your_api_key_here"
      }
    }
  }
}

Note: Replace /path/to/secure-annex-mcp with the absolute path to your SecureAnnex MCP server directory.

Project Structure

secure-annex-mcp/
├── pyproject.toml         # Package configuration
├── README.md              # Project documentation
└── secure_annex_mcp/      # Main package
    ├── __init__.py        # Package initialization
    ├── __main__.py        # Entry point when run as a module
    └── server.py          # MCP server implementation

Available Tools

Extension Search and Information

  • search_extensions: Search for browser extensions based on various criteria

    • Parameters: name, extension_id, owner, featured, active, page, page_size
  • get_extension_details: Get detailed information about a specific extension

    • Parameters: extension_id (required)
  • get_extension_versions: Get version history for a specific extension

    • Parameters: extension_id (required), version

Security Analysis

  • get_extension_vulnerabilities: Get security vulnerabilities for a specific extension

    • Parameters: extension_id (required), version
  • get_extension_signatures: Get security signatures for a specific extension

    • Parameters: extension_id (required), version, rule
  • get_extension_urls: Get network URLs used by a specific extension

    • Parameters: extension_id (required), version, domain
  • get_extension_manifest_risks: Get manifest permission risks for a specific extension

    • Parameters: extension_id (required), version, risk_type
  • get_extension_analysis: Get AI security analysis for a specific extension

    • Parameters: extension_id (required)
  • get_extension_code_review: Get code security review for a specific extension

    • Parameters: extension_id (required), version

User Feedback

  • get_extension_reviews: Get user reviews for a specific extension
    • Parameters: extension_id (required), rating

Updates

  • get_recent_updates: Get recently updated extensions
    • Parameters: None

Example Usage

Here are some practical examples of how to use the tools with Claude:

Searching for Extensions

# Get all extensions developed by specific developer
I need to find all extensions by help@getadblock.com

# Claude would use:
{
  "name": "search_extensions",
  "arguments": {
    "owner": "help@getadblock.com"
  }
}

Security Analysis

# Get all security signatures for an extension
Show me all security signatures for the AdBlock extension

# Claude would use:
{
  "name": "get_extension_signatures",
  "arguments": {
    "extension_id": "gighmmpiobklfepjocnamgkkbiglidom"
  }
}

# Extract all network domains from an extension
Extract all domains embedded in the AdBlock extension

# Claude would use:
{
  "name": "get_extension_urls",
  "arguments": {
    "extension_id": "gighmmpiobklfepjocnamgkkbiglidom"
  }
}

# Analyze manifest permissions
Show me a table of all permissions requested by AdBlock with explanations

# Claude would use:
{
  "name": "get_extension_manifest_risks",
  "arguments": {
    "extension_id": "gighmmpiobklfepjocnamgkkbiglidom"
  }
}

Integration with Other MCPs

# Leveraging VirusTotal MCP for domain reputation
Can you extract all domains from the AdBlock extension and check their reputation on VirusTotal?

# Claude would use both SecureAnnex and VirusTotal MCPs:
# 1. First, get domains from SecureAnnex
{
  "name": "get_extension_urls",
  "arguments": {
    "extension_id": "gighmmpiobklfepjocnamgkkbiglidom"
  }
}

# 2. Then for each domain, check VirusTotal
{
  "name": "domain_report",  // VirusTotal MCP tool
  "arguments": {
    "domain": "example.com"  // For each domain found
  }
}

# 3. Claude would compile results into a table:
| Domain | Reputation | Detection Ratio | Categories |
|--------|------------|-----------------|------------|
| domain1.com | Clean | 0/85 | Advertising |
| domain2.com | Suspicious | 3/85 | Marketing |

Comprehensive Analysis

# Request a complete security review of an extension
Perform a full security audit of the AdBlock extension

# Claude would combine multiple tools:
{
  "name": "get_extension_details",
  "arguments": {
    "extension_id": "gighmmpiobklfepjocnamgkkbiglidom"
  }
}

{
  "name": "get_extension_vulnerabilities",
  "arguments": {
    "extension_id": "gighmmpiobklfepjocnamgkkbiglidom"
  }
}

{
  "name": "get_extension_analysis",
  "arguments": {
    "extension_id": "gighmmpiobklfepjocnamgkkbiglidom"
  }
}

API Key

The SecureAnnex MCP server requires an API key for authentication with the SecureAnnex API. Obtain your API key from the SecureAnnex service and include it in the Claude Desktop configuration as shown above.

Troubleshooting

If you encounter any issues:

  1. Ensure your API key is correctly set in the environment variables
  2. Verify the path in your Claude Desktop configuration is correct

相关推荐

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Alexandru Strujac
  • Efficient thumbnail creator for YouTube videos

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Lists Tailwind CSS classes in monospaced font

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • https://appia.in
  • Siri Shortcut Finder – your go-to place for discovering amazing Siri Shortcuts with ease

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • Daren White
  • A supportive coach for mastering all Spanish tenses.

  • J. DE HARO OLLE
  • Especialista en juegos de palabras en varios idiomas.

  • apappascs
  • 发现市场上最全面,最新的MCP服务器集合。该存储库充当集中式枢纽,提供了广泛的开源和专有MCP服务器目录,并提供功能,文档链接和贡献者。

  • ShrimpingIt
  • MCP系列GPIO Expander的基于Micropython I2C的操作,源自ADAFRUIT_MCP230XX

  • jae-jae
  • MCP服务器使用剧作《无头浏览器》获取网页内容。

  • HiveNexus
  • 一个适用于中小型团队的AI聊天机器人,支持DeepSeek,Open AI,Claude和Gemini等车型。 专为中小团队设计的ai聊天应用,支持deepSeek,打开ai,claude,双子座等模型。

  • ravitemer
  • 一个功能强大的Neovim插件,用于管理MCP(模型上下文协议)服务器

  • patruff
  • Ollama和MCP服务器之间的桥梁,使本地LLMS可以使用模型上下文协议工具

    Reviews

    3 (1)
    Avatar
    user_FySaP4fJ
    2025-04-16

    As an ardent user of secure-annex-mcp by arsolutioner, I couldn't be more impressed. This solution offers exceptional security features and seamless integration within our systems. It’s user-friendly and highly reliable. The GitHub repository is well-documented, ensuring straightforward implementation. Highly recommend to anyone in need of robust security measures!