ta0ing/mcp-securitytools

This page was translated automatically. Technical details may differ from the original. View the original

410 stars 23 forks Quality 56 Trend 19

MCP-SecurityTools is an open-source project focused on collecting and updating MCP in the field of cybersecurity, aiming to compile, organize, and optimize various security tools, technologies, and practical experience related to MCP.

Overview

MCP (Model Context Protocol) is an open protocol used to standardize how applications provide context to LLMs. MCP can be thought of as the USB-C interface for AI applications. Just as USB-C provides standardized ways for devices to connect various peripherals and accessories, MCP provides a standardized way for AI models to connect different data sources and tools. MCP helps you build agents and complex workflows on top of LLMs. LLMs often need to integrate with data and tools, and MCP offers: - Pre-built integration lists your LLMs can access directly - Flexibility to switch between different LLM providers and vendors - Best practices for protecting data in your infrastructure Essentially, MCP follows a client-server architecture, where host applications can connect to multiple servers: : Programs like Claude, Cherry Studio client, IDE, or AI tools that want to access data via MCP. - : Protocol clients maintaining a 1:1 connection to the server - : Lightweight programs that expose specific functions through standardized model context protocols - : Computer files, databases, and services that MCP servers can securely access - : External systems provided over the internet that MCP servers can connect to (e.g., via APIs) For detailed tutorials on using Cherry StudioMCP, see: https://docs.cherry-ai.com/advanced-basic/mcp https://github.com/BurtTheCoder/mcp-virustotal·

Overview (machine translated)

**MCP-SecurityTools is an open-source project focused on collecting and updating MCP in the field of cybersecurity, aiming to summarize, organize, and optimize various security tools, technologies, and practical experience related to MCP. **

mcp name	Introduction
uncover-MCP	Enables AI to invoke FOFA/SHODAN.
ENScan_GO-MCP	Enables AI to collect information with one click
VirusTotal-MCP	Enabling AI to have VirusTotal’s secure analysis capabilities
cloudsword-MCP	Enabling AI to have cloud security capabilities—in a word, it penetrates the cloud environment
ZoomEye-MCP	Enable AI to query ZoomEye to obtain network asset information
AWVS-MCP	Enables AI to call AWVS for vulnerability scanning
GhidraMCP	To be updated, planned
IDA-MCP	To be updated, planned
Nmap-MCP	To be updated, planned

Zero: Introduction

0.1 Why Choose MCP?

MCP helps you build agents and complex workflows on top of LLMs. LLMs often need to integrate with data and tools, and MCP offers:

Pre-built integrated lists so your LLMs can be directly accessed
Flexibility in switching between different LLM providers and vendors
Best practices for protecting data in your infrastructure

0.2 Overall Architecture

Essentially, MCP follows a client-server architecture, where host applications can connect to multiple servers:

MCP Host: Programs like Claude, Cherry Studio client, IDE, or AI tools that want to access data via MCP.

MCP Client: A protocol client that maintains a 1:1 connection with the server
MCP Server: A lightweight program that exposes specific functions through standardized model context protocols
Local Data Source: Computer files, databases, and services that the MCP server can securely access
Remote Services: External systems provided over the internet that MCP servers can connect to (e.g., via APIs)

1: uncover-MCP (enables AI to call FOFA/SHODAN)

Project Address: 'https://github.

This page was translated automatically. Technical details may differ from the original.

Install

uvx mcp-server-zoomeye

New to MCP? Start with the mcpskill.org guide →

Configuration

{
    "mcpServers": {
        "uncover-mcp": {
            "command": "./uncover-mcp",
            "args": [],
            "env": {
                "SHODAN_API_KEY": "",
                "FOFA_EMAIL": "",
                "FOFA_KEY": ""
            }
        }
    }
}