mcpField
X
Xray Mcp

Xray Mcp

Local
github.com/zhangning77-techSecurity1Updated 62w ago

About Xray Mcp

Xray Mcp connects MCP clients to xray vulnerability scanning for ModelScope hosting. It provides URL scans with configurable scan types and options, plus scanner version information.

Key features

  1. 01Scan target URLs
  2. 02Choose crawler scan type
  3. 03Configure timeout, plugins, and POC
  4. 04Return detailed JSON results
  5. 05Get xray version information

Use cases

  1. 01Scan a hosted URL for vulnerabilities
  2. 02Select a crawler mode for a scan
  3. 03Check the installed xray version

MCP support

The server implements MCP tools for xray scanning and version lookup, designed for integration with ModelScope's MCP platform. Proxy and non-HTTP service scanning tools are marked as planned.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Xray MCP Server

This is an enhanced MCP (Model Context Protocol) server that provides xray vulnerability scanning capabilities for ModelScope hosting.

Features

  • xray_scan: Perform vulnerability scans on target URLs

    • Support for basic-crawler and phantasm-crawler scan types
    • Configurable timeout
    • Plugin and POC support
    • JSON output with detailed results
  • xray_version: Get xray version information

  • xray_start_proxy: Start xray in passive proxy mode (planned)

    • Configurable proxy port
    • Real-time vulnerability detection
  • xray_stop_proxy: Stop the running xray proxy (planned)

  • xray_service_scan: Scan services on non-HTTP targets (planned)

    • Port range scanning
    • Service detection

Installation

  1. Install Python 3.7+
  2. Install xray from https://github.com/chaitin/xray
  3. Set the XRAY_PATH environment variable to point to your xray binary:
    export XRAY_PATH=/path/to/xray
    

Configuration

Environment variables:

  • XRAY_PATH: Path to xray binary (default: "xray")
  • XRAY_CONFIG_DIR: Configuration directory (default: "~/.xray-mcp")
  • XRAY_OUTPUT_DIR: Output directory for scan results (default: system temp)

Usage

For ModelScope MCP

This server is designed to work with ModelScope's MCP platform. The server implements the MCP protocol and can be integrated into the ModelScope ecosystem.

Standalone Usage

Run the server:

python server.py

The server reads JSON-RPC requests from stdin and writes responses to stdout.

Example Request
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "xray_scan",
    "arguments": {
      "target": "http://example.com",
      "scan_type": "basic-crawler",
      "timeout": 300
    }
  }
}

Available Tools

xray_scan

Performs a vulnerability scan on a target URL.

Parameters:

  • target (required): The target URL to scan
  • scan_type (optional): Type of scan - "basic-crawler" or "phantasm-crawler" (default: "basic-crawler")
  • timeout (optional): Scan timeout in seconds (default: 300)
  • plugins (optional): Comma-separated list of plugins to use
  • poc (optional): POC to use for scanning
xray_version

Gets the version information of the installed xray scanner.

No parameters required.

xray_start_proxy (Planned)

Starts xray in passive proxy mode for real-time scanning.

Parameters:

  • port (optional): Proxy port to listen on (default: 7777)
xray_stop_proxy (Planned)

Stops the running xray proxy.

No parameters required.

xray_service_scan (Planned)

Scans services on non-HTTP targets.

Parameters:

  • target (required): The target host/IP to scan
  • port_range (optional): Port range to scan (default: "1-65535")
  • timeout (optional): Scan timeout in seconds (default: 300)

Security Considerations

  • The server executes xray with user-provided URLs
  • Implement appropriate access controls when deploying
  • Consider rate limiting for production use
  • Validate and sanitize all inputs

License

MIT License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.