Search

Security-first, version-agnostic MCP gateway for Odoo 17/18/19 — works with stock and custom modules via YAML configuration

LLM security middleware: prompt-injection detection, PII protection, tool policy, cost tracking. Python port of ai-shield-core.

Open-source security firewall for MCP (Model Context Protocol) servers. Scan, monitor, and enforce policies on AI agent tool calls.

Pre-flight checks for MCP servers: passive token footprint, use-case scoping, security, and name safety. LLM-facing quality scorecard.

Multi-language code quality auditor with MCP server - Analyze TypeScript, JavaScript, and Go code for SOLID principles, DRY violations, security patterns, and more

Enterprise-grade MCP server for Optimizely Feature and Web Experimentation platforms with AI-powered natural language interface, comprehensive security, and performance optimization

Black Duck MCP brings Signal's AI-powered security analysis directly into your development environment. Provides vulnerability detection through the Model Context Protocol.

npm audit for MCP servers — zero-config heuristic testing that discovers tools and runs 21 automated security & quality checks per tool

Security-first MCP server. Sanitizes web content before it reaches your LLM — strips prompt injection, redacts PII, and reduces token consumption by up to 70%.

MCP server for Kali Linux penetration testing - 139 tools for AI-assisted security testing - Giving Agents access to full pentesting tools

Local-first, security-first TypeScript agent runtime — caste-based RBAC, default-deny tools, MCP-native, runs entirely on your machine.

Security scanner for MCP server configurations. Finds risky tools, vulnerable packages, and suspicious servers across Claude Desktop, Cursor, VS Code, and more.

Security scanner for AI-generated apps. Detects exposed API keys, validates them against live services, and exposes itself as an MCP server for AI coding agents.

Security-first local AI assistant for Linux — agentic runtime with policy enforcement, multi-provider support, voice channel, Discord, and full auditability

ARKO Model Context Protocol server — brings the ARKO security control engine into Claude Code, Cursor, and any MCP-compatible AI coding agent.

MCP server for Scannd (scannd.com) — trigger security scans and read reports/vulnerabilities from AI agents. Talks to the hosted Scannd REST API.

MCP Checkpoint continuously secures and monitors Model Context Protocol operations through static and dynamic scans, revealing hidden risks in agent-to-tool communications.

Agent-embedded security monitor. Instruments the four agent boundaries (model-client, framework tool-dispatch, MCP, effect) and reports findings to a control plane.

ddot -- The Security Protocol for Agentic AI. Ed25519 signing, Wasm sandboxing, 5-layer prompt firewall, and tamper-evident audit chains for MCP servers.

Deterministic security proxy for MCP tool calls. Blocks dangerous requests, redacts secrets from responses, catches prompt injection. No AI, no cloud, pure rules.