Real-time prompt injection and jailbreak detection for AI agents. Blocks instruction overrides, data exfiltration, tool poisoning and 8 attack types. Now with shared learning brain - confirmed attacks
Security through absurdity: transforms SQL injection and XSS attempts into harmless comedy responses using AI-powered humor defense.
Audits any MCP server for command injection, path traversal, missing auth, hardcoded secrets, SQL injection, SSRF and tool poisoning. Returns grade A-F with CVE references. Malicious servers flagged n
Security intelligence for AI agents: password breach checks (900M+ HIBP hashes), email/domain/IP/URL reputation, prompt injection detection (200+ patterns), and skill supply chain scanning. Pay-per-re
Two-tier memory with hot cache (instant injection) and cold semantic search. Auto-promotes frequently-used patterns, extracts knowledge from Claude outputs, and organizes via knowledge graph relations
Find hands-on secure coding labs for vulnerabilities like XSS, SQL Injection, and OWASP Top 10 topics. Get a personalized learning pathway based on your GitHub or SecDim profile to accelerate your rem
A MCP server for LocalStack to manage local AWS environments, including lifecycle operations, infra deployments, log analysis, fault injection, and state management.
A zero-cost MCP server that forces AI to self-correct generation messages using prompt injection, independent self-audition and context isolation.
PostgreSQL MCP server with 14 tools for querying, schema exploration, and table analysis. Features security-first design with SQL injection prevention and read-only by default.
Beelzebub is a honeypot framework that lets you build honeypot tools using MCP. Its purpose is to detect prompt injection or malicious agent behavior. The underlying idea is to provide the agent with
Free AI agent skill security scanner. Scan SKILL.md, MCP configs, and system prompts for credential theft, prompt injection, zero-width character attacks, and ClawHavoc indicators. Supports OpenClaw,
Scans GitHub repositories and skills for vulnerabilities like prompt injection, malware, and OWASP risks. Identifies security threats in external dependencies to ensure software health. Provides detai
EU AI Act compliance scanner for Python AI agents. Scans, analyzes, and remediates LangChain/CrewAI/AutoGen/OpenAI code across 6 articles with 10 tools including prompt injection detection, risk class
MCP server for Godot 4.x with runtime control via injected UDP bridge: input simulation, screenshots, UI discovery, and live GDScript execution while the game is running.
AI-safe secrets manager with MCP integration. Run commands with credentials injected as environment variables - AI agents never see plaintext secrets. Features output sanitization, AES-256-GCM encrypt
Cryptographic authorization for AI agents. Scoped delegation, checkpoint escalation, Ed25519 signed receipts. Block prompt injection at the tool boundary.
Provide AI-powered security analysis and safety instruction tools to protect AI agents during MCP interactions. Analyze text content for harmful or inappropriate material and enhance user prompts with
<p align="center"> <a href="https://github.com/trimstray/the-book-of-secret-knowledge"> <img src="https://github.com/trimstray/the-book-of-secret-knowledge/blob/master/static/img/the-book-of-secret-kn
Automate complex web browsing tasks like navigation, form filling, and deep research across multiple tabs. Extract structured data and visual insights from any webpage instantly. Streamline digital wo
# Vulcan File Ops MCP Server