SecurityMCP AI 对话、文档检索与安全扫描命令行工具

SecurityMCP 是一款支持与 Anthropic 模型进行 AI 对话、文档检索、MCP 命令扩展及文件安全风险扫描的命令行应用程序,适用于开发调试与安全分析场景。

  • by NetskopeScripter12
  • Python
  • 本地部署
  • 更新于
在 GitHub 查看 NetskopeScripter12/SecurityMCP

使用说明

SecurityMCP

SecurityMCP is a command-line interface application based on Anthropic's Introduction to MCP course that enables interactive chat capabilities with AI models through the Anthropic API. The application supports document retrieval, command-based prompts, and extensible tool integrations via the MCP (Model Control Protocol) architecture. There are security safeguards inside the MCP's instructions that block the reading of malicious files, only allowing you to edit them. There is also the added capability of Security Risk Scanning via the Security+ command.

Prerequisites

  • Python 3.9+
  • Anthropic API Key

Setup

Step 1: Configure the environment variables

  1. Create or edit the .env file in the project root and verify that the following variables are set correctly:
ANTHROPIC_API_KEY=""  # Enter your Anthropic API secret key

Step 2: Install dependencies

Option 1: Setup with uv (Recommended)

uv is a fast Python package installer and resolver.

  1. Install uv, if not already installed:
pip install uv
  1. Create and activate a virtual environment:
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
  1. Install dependencies:
uv pip install -e .
  1. Run the project
uv run main.py

Option 2: Setup without uv

  1. Create and activate a virtual environment:
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
  1. Install dependencies:
pip install anthropic python-dotenv prompt-toolkit "mcp[cli]==1.8.0"
  1. Run the project
python main.py

Usage

Basic Interaction

Simply type your message and press Enter to chat with the model.

Document Retrieval

Use the @ symbol followed by a document ID to include document content in your query:

> Tell me about @deposition.md

Commands

Use the / prefix to execute commands defined in the MCP server

Acceptible Commands

Convert file to Markdown

> /format [filename] 

Scan files and give it a security rating

> /security+ [filename]

Commands will auto-complete when you press Tab.

Development

Adding New Documents

Edit the mcp_server.py file to add new documents to the docs dictionary.