Red-team-mcp
Description
# Red-team-mcp An MCP (Model Context Protocol) server for AI agents to use during red teaming exercises. ## Overview This server provides resources and tools for AI agents to access during red teaming scenarios. It implements the Model Context Protocol to allow AI agents to…
About
# Red-team-mcp An MCP (Model Context Protocol) server for AI agents to use during red teaming exercises. ## Overview This server provides resources and tools for AI agents to access during red teaming scenarios. It implements the Model Context Protocol to allow AI agents to retrieve information, access tools, and…
Details
- Author
- skjortan23
- GitHub stars
- 16
- Downloads
- 470
- Categories
- Other, AI
Jump to
- High-speed port scanning via masscan integration
- Vulnerability detection using Nuclei templates
- SSH command execution and brute-force capabilities
- Metasploit exploit database with fast search
- Exploit execution against targets with payload configuration
- Domain discovery using subfinder
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Red-team-mcpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Set up external dependencies (MongoDB, nuclei, masscan), populate the Metasploit exploits database using the provided scripts, and ensure the Metasploit RPC server is running. Then configure an MCP client to connect to the server, and use the available tools and resources for security testing tasks.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"red-team-mcp": {
"read-team-mcp-server": {
"command": "python",
"args": [
"scripts/setup_exploits_db.py"
]
}
}
}
}McpServers
{
"read-team-mcp-server": {
"command": "python",
"args": [
"scripts/setup_exploits_db.py"
]
}
}Red-team-mcp
An MCP (Model Context Protocol) server for AI agents to use during red teaming exercises.Overview
This server provides resources and tools for AI agents to access during red teaming scenarios. It implements the Model Context Protocol to allow AI agents to retrieve information, access tools, and perform actions needed for security testing and evaluation.Architecture
graph TD
Agent[AI Agent Client] <--> |MCP Protocol| Server[FastMCP Server]
subgraph "MCP Server Components"
Server --> PortScanner[Port Scanner Module]
Server --> VulnScanner[Vulnerability Scanner Module]
Server --> SSHTools[SSH Tools Module]
Server --> Metasploit[Metasploit Integration]
Server --> DomainDiscovery[Domain Discovery Module]
Server <--> Database[(MongoDB Database)]
end
subgraph "External Tools"
PortScanner --> Masscan[masscan]
VulnScanner --> Nuclei[nuclei]
SSHTools --> SSH[SSH Client]
Metasploit --> MSFRPC[Metasploit RPC]
DomainDiscovery --> Subfinder[subfinder]
end
Database --> Findings[Findings]
Components
1. Port Scanner
- Integrates with masscan for high-speed port scanning - Allows AI agents to discover open ports and services on target networks - Configurable scan parameters (IP ranges, port ranges, scan rate) - Results parsing and formatting for agent consumption2. Vulnerability Scanner
- Integrates with Nuclei for vulnerability detection - Supports custom templates and severity filtering - Stores results in MongoDB for fast searching3. SSH Tools
- SSH command execution with credential authentication - SSH brute force capabilities with username/password lists - Results stored with host and port information4. Metasploit Integration
- Exploit Database: Pre-populated MongoDB collection with all Metasploit exploits - Fast Search: Search exploits by platform, CVE, rank, author, or keywords - Exploit Execution: Execute exploits against targets with payload configuration - Live Querying: Real-time exploit listing from Metasploit RPC serverImplementation Plan
1. Set up basic MCP server structure 2. Implement masscan integration with parameter validation 3. Create result parsing and storage mechanisms 4. Add additional components (forthcoming) 5. Implement logging and monitoring 6. Build permission and boundary systemsTodos
- [x] Add nuclei scanner - [x] Add SSH scanner - [x] Add Metasploit integration - [x] Implement fully asynchronous FastMCP server - [ ] Add tests - [ ] Prompt for step by step hacking of a machine. (See agents/simple_agent.py)Setup
installing 3rp party tools
The setup is depending on the following tools
- mongodb
- nuclei
-
Exploit Database Setup
To enable fast exploit searching, populate the Metasploit exploits database:1. Prerequisites:
- Metasploit Framework installed
- MongoDB running on localhost:27017
- Metasploit RPC server running: msfrpcd -P msf -a 127.0.0.1
- Python dependencies: pip install pymetasploit3
2. Populate Database:
python scripts/setup_exploits_db.py
3. Test Setup:
python scripts/test_exploits_db.py
This creates a searchable database of all Metasploit exploits with metadata including:
- CVE references
- Platform information
- Exploit rank and author
- Compatible payloads
- Required options
Usage
Exploit Search Examples
```pythonSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
