- Home
- MCP servers
- PocGenius
PocGenius
- python
2
GitHub Stars
python
Language
5 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"rockmelodies-pocgeneratormcp": {
"command": "python",
"args": [
"/path/to/pocgenius/server.py"
]
}
}
}PocGenius is an MCP server that generates safe, standards-compliant POC code for vulnerability verification. It creates pocsuite3 compatible proofs of concept based on your vulnerability details, automating structure, validation, and secure execution to help you test responsibly.
How to use
You use PocGenius by connecting an MCP client to the server and sending vulnerability information. The server responds with a ready-to-run POC that follows best practices, including multi-layer validation, randomized parameters to reduce false positives, and safeguards to avoid harming target systems. You can trigger POC generation for different vulnerability types (for example RCE, SQLi, XSS, and more) and tailor the verification flow through structured input.
How to install
Prerequisites: Python 3.8 or newer and the pocsuite3 framework.
Step-by-step commands to set up PocGenius locally:
# Step 1: Clone the PocGenius project
git clone <repository-url>
cd pocgenius
# Step 2: Install dependencies
pip install -r requirements.txt
Additional sections
Configuration for MCP client: you can register PocGenius as an MCP server by providing a stdio entry that launches the server script directly. The following example shows how to connect a client to PocGenius using Python. You would place the snippet in your MCP client configuration.
{
"mcpServers": {
"pocgenius": {
"command": "python",
"args": ["/path/to/pocgenius/server.py"]
}
}
}
Available tools
POC Generation
Generates pocsuite3 compatible POC code from structured vulnerability input with context-aware logic and multi-step validation.
Security Filtering
Applies safety filters to generated payloads, removing dangerous instructions and potential destructive actions.
Randomization
Introduces randomized parameters to avoid fixed values and reduce false positives across runs.
Environment Recovery
Ensures the testing environment can be restored to its original state after POC execution.
Result Parsing
Delivers clear, structured results including success criteria and logs for reproducibility.