MCP for Security is a collection of server implementations that make various security testing tools accessible through a standardized interface called Model Context Protocol (MCP). This enables seamless integration of security tools into automated workflows and platforms while providing a consistent way to interact with different security tools.
The simplest way to use MCP servers is through Docker:
docker pull cyprox/mcp-for-security
You can then run any of the MCP servers using Docker. This approach is recommended as it eliminates dependency conflicts and ensures consistent execution environments.
If you prefer a manual installation, you can use the provided setup script:
# Clone the repository
git clone https://github.com/cyproxio/mcp-for-security.git
cd mcp-for-security
# Run the setup script
./start.sh
Note that each tool may have specific dependencies. For best results, refer to the documentation for the specific MCP server you want to use.
MCP for Security provides standardized interfaces for numerous security tools across different categories:
A pattern-based wordlist generator for subdomain discovery.
docker run cyprox/mcp-for-security alterx-mcp
An advanced subdomain enumeration tool with both passive and active capabilities.
docker run cyprox/mcp-for-security amass-mcp
A passive subdomain discovery tool that finds domains related to the target.
docker run cyprox/mcp-for-security assetfinder-mcp
Discovers subdomains by querying SSL certificate transparency logs.
docker run cyprox/mcp-for-security crtsh-mcp
A web content fuzzing tool for discovering hidden files and directories.
docker run cyprox/mcp-for-security ffuf-mcp
Analyzes HTTP security headers against OWASP standards.
docker run cyprox/mcp-for-security http-headers-security-mcp
A fast web crawler with JavaScript parsing and hybrid crawling support.
docker run cyprox/mcp-for-security katana-mcp
A fast port scanner for large-scale network discovery.
docker run cyprox/mcp-for-security masscan-mcp
A comprehensive network scanning tool for service and vulnerability discovery.
docker run cyprox/mcp-for-security nmap-mcp
A template-based vulnerability scanner with an extensive library of security checks.
docker run cyprox/mcp-for-security nuclei-mcp
An advanced SQL injection detection and exploitation tool.
docker run cyprox/mcp-for-security sqlmap-mcp
A mobile security framework for analyzing mobile applications.
docker run cyprox/mcp-for-security mobsf-mcp
Each MCP server follows a standardized interface pattern. Here's a general example of how to use an MCP server:
// Example of using an MCP client to interact with an MCP server
const client = new MCPClient("http://localhost:8080");
// Configure the scan parameters
const params = {
target: "example.com",
// Tool-specific parameters here
};
// Start the scan
const result = await client.scan(params);
console.log(result);
const scanResult = await client.scan({
target: "192.168.1.1",
ports: "1-1000",
arguments: "-sV -sC"
});
const scanResult = await client.scan({
url: "https://vulnerable-website.com/page.php?id=1",
level: 3,
risk: 2,
techniques: "BEUSTQ"
});
const scanResult = await client.scan({
target: "https://example.com",
templates: "cves,vulnerabilities",
severity: "critical,high"
});
Many MCP servers support additional configuration options for fine-tuning the scan behavior:
const scanResult = await client.scan({
target: "example.com",
rate: 100 // Requests per second
});
const scanResult = await client.scan({
target: "example.com",
outputFormat: "json" // Output format (json, xml, etc.)
});
const scanResult = await client.scan({
target: "https://secure-site.com",
username: "user",
password: "pass"
});
Each tool provides specific capabilities and parameters. For detailed documentation on each tool, refer to the individual tool's documentation linked in the project repository.
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "security-tools-bridge" '{"command":"npx","args":["-y","@cyproxio/mcp-for-security"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"security-tools-bridge": {
"command": "npx",
"args": [
"-y",
"@cyproxio/mcp-for-security"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"security-tools-bridge": {
"command": "npx",
"args": [
"-y",
"@cyproxio/mcp-for-security"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect