PrismSec
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
PrismSec π·
Secure, modular MCP server for pentesting tools.
Wraps 7 industry-standard security tools (nmap, nuclei, gobuster, subfinder, httpx, nikto, sqlmap) into 13 registered MCP tools β ready to use with Claude, Cursor, Copilot, and any MCP-compatible AI agent.
Features
Feature | Description |
Zero shell=True | All subprocess calls use |
Input validation | Target, URL, port, severity β all validated before execution |
Injection detection | Blocks shell metacharacters ( |
Timeout enforcement | Every tool has configurable timeout β auto-kills hung processes |
Structured output | Parsed XML/JSON/text β clean JSON for AI agents |
Modular architecture | One file per tool β easy to add, maintain, and test |
MCP SDK v2 | Built on the latest Model Context Protocol SDK |
Related MCP server: Kali Tools MCP Server
Installation
From source
git clone https://github.com/azmisyahrul/prismsec.git
cd prismsec
pip install -e .Prerequisites
Install the security tools you need:
# Ubuntu/Debian
apt install nmap nikto sqlmap
# Go-based tools
go install -v github.com/projectdiscovery/nuclei/v3/cmd/nuclei@latest
go install -v github.com/projectdiscovery/subfinder/v2/cmd/subfinder@latest
go install -v github.com/projectdiscovery/httpx/cmd/httpx@latest
go install github.com/OJ/gobuster/v3@latestTools (13 registered)
Nmap β Port Scanning
MCP Tool | Description |
| Port scan with quick/full/service/stealth/aggressive modes |
| Service/version detection on open ports |
| Scan all 65535 TCP ports |
Nuclei β Vulnerability Scanning
MCP Tool | Description |
| Full vulnerability scan with all templates |
| Scan filtered by severity (critical, high, etc.) |
| Targeted scan with specific template |
Gobuster β Directory/DNS Brute
MCP Tool | Description |
| Directory brute-force with configurable extensions |
| DNS subdomain brute-force |
Other Tools
MCP Tool | Description |
| Passive subdomain enumeration (crt.sh, VirusTotal, etc.) |
| Web probing β alive detection, titles, tech fingerprinting |
| Web server vulnerability scanning |
| SQL injection detection and testing |
Meta
MCP Tool | Description |
| Check which security tools are installed |
Usage
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"prismsec": {
"command": "python3",
"args": ["/path/to/prismsec/server.py"],
"env": {}
}
}
}Claude Code
claude mcp add prismsec python3 /path/to/prismsec/server.pyCursor / Windsurf / Cline
Add to .cursor/mcp.json or equivalent:
{
"mcpServers": {
"prismsec": {
"command": "python3",
"args": ["/path/to/prismsec/server.py"]
}
}
}SSE Transport (Remote)
# Server side
python3 server.py --transport sse --host 0.0.0.0 --port 8000
# Client config
{
"mcpServers": {
"prismsec": {
"url": "http://localhost:8000/sse"
}
}
}Project Structure
prismsec/
βββ server.py # MCP server entry point (13 tools)
βββ pyproject.toml # Project config + dependencies
βββ tools/ # Tool wrappers (one file per tool)
β βββ base.py # ToolWrapper ABC + async runner
β βββ nmap.py # Nmap β XML parsing, scan modes
β βββ nuclei.py # Nuclei β JSON output parsing
β βββ gobuster.py # Gobuster β text output parsing
β βββ subfinder.py # Subfinder β subdomain enum
β βββ httpx.py # Httpx β web probing
β βββ nikto.py # Nikto β web vuln scan
β βββ sqlmap.py # Sqlmap β SQL injection testing
βββ parsers/ # Output parsers
β βββ xml_parser.py # nmap XML β structured JSON
β βββ json_parser.py # JSON/JSONL parsing
β βββ text_parser.py # Gobuster, nikto, sqlmap text
βββ utils/ # Shared utilities
βββ runner.py # AsyncRunner with timeout
βββ validator.py # Input validation + injection detection
βββ rate_limiter.py # Token bucket rate limiter
βββ logging.py # Structured loggingConfiguration
Environment Variable | Default | Description |
|
| Logging level (DEBUG, INFO, WARNING, ERROR) |
Security Considerations
β οΈ Authorized testing only. Use against systems you own or have written permission to test.
Tool outputs may contain sensitive information (IPs, open ports, vulnerabilities)
The server binds to
127.0.0.1by default β never expose to untrusted networksEach tool has configurable timeouts to prevent resource exhaustion
License
MIT
Built with the Model Context Protocol standard for broad client compatibility.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
Related MCP Connectors
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.
AI-security knowledge as MCP: standards-mapped tools (OWASP, NIST, MITRE) for AI agents.
Safety tools for AI agents: safe page reader, prompt-injection, secrets, PII and MCP server scans
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceAn MCP server that exposes over 20 standard penetration testing utilities, such as Nmap, SQLMap, and OWASP ZAP, as callable tools for AI agents. It enables natural language control over complex security workflows for automated and interactive penetration testing.117-
- AlicenseNot gradedqualityDmaintenanceIntegrates 7 security tools (nmap, nuclei, dirsearch, sqlmap, hydra, Acunetix, Metasploit) via MCP protocol for AI-assisted penetration testing with enterprise-grade safety features.1MIT
- FlicenseNot gradedqualityDmaintenanceAI-powered Attack Surface Intelligence server that exposes industry-standard penetration testing tools via MCP, enabling AI agents to perform comprehensive security assessments.3-
- AlicenseCqualityDmaintenanceAI-powered security scanning MCP server that exposes 25+ professional tools, enabling penetration testing and security assessments through natural language interaction with AI agents like Claude Desktop.31MIT