About MCP Nuclei Server
MCP Nuclei Server is an MCP-based service that lets large language models run Nuclei security scans and receive results in JSON. It is aimed at users who want to call Nuclei from an AI client such as Cline for security testing.
Key features
- 01Run Nuclei security scans
- 02Template and tag filtering
- 03Filter findings by severity
- 04JSON formatted scan results
Use cases
- 01Having an LLM launch vulnerability scans against a target in Cline
- 02Reviewing scan results filtered by severity
MCP support
The project is an MCP server that offers Nuclei scanning to MCP clients, accepting parameters such as target, templates and severity and returning JSON results.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README
MCP Nuclei Server
A Nuclei security scanning server based on MCP (Model Control Protocol), providing convenient vulnerability scanning services.
Project Introduction
MCP Nuclei Server is a Nuclei security scanning service developed based on the MCP protocol. It allows large language models to execute Nuclei security scans, supporting various scanning options and result output formats.
Key Features:
- Support for Nuclei security scanning
- Configurable template and tag filtering
- Support for severity-based vulnerability filtering
- JSON format output results
- Easy-to-integrate MCP service
Installation Guide
Prerequisites
- Python 3.8 or higher
- Nuclei binary (installed and configured)
Installation Steps
- Clone the repository:
git clone https://github.com/crazyMarky/mcp_nuclei_server.git
cd mcp_nuclei_server
- Install UV and activate environment:
curl -LsSf https://astral.sh/uv/install.sh | sh # Linux/Mac
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" # Windows
- Install dependencies:
# Create and activate virtual environment
uv venv
source .venv/bin/activate
# Install mcp related packages
uv pip install mcp
Usage Guide
MCP Configuration (Example for CLINE)
- Reference MCP JSON configuration:
{
"mcpServers": {
"nuclei_mcp_server": {
"command": "/path/to/uv", # path to uv
"args": [
"--directory",
"/path/to/nuclei_mcp_server/",
"run",
"main.py"
],
"env": {
"NUCLEI_BIN_PATH": "/path/to/nuclei"
}
}
}
}
Usage Example
Parameter Description
target: Target URL or IP addresstemplates: List of specific templates to use (optional)severity: Vulnerability severity filter (critical, high, medium, low, info)template_tags: Template tag filter (optional)output_format: Output format (default: "json")
Output Format
Scan results are returned in JSON format with the following fields:
{
"success": true,
"target": "https://example.com",
"time_cost_seconds": 10.5,
"results": [
{
"template": "template-name",
"severity": "high",
"matched_at": "https://example.com/path",
"info": {
"name": "Vulnerability Name",
"description": "Vulnerability Description"
}
}
]
}
Contributing
Issues and Pull Requests are welcome!
- Fork the project
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details
Contact
For any questions or suggestions, please contact us through:
- Submit an Issue
Comments
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.