8514 matches found
CVE-2026-33980
CVE-2026-33980 — KQL Injection in adx-mcp-server via tablename parameter Severity : High CVSS 8.3 CWE : CWE-943 — Improper Neutralization of Special Elements in Data Query Logic Affected : adx-mcp-server = 1.1.0 Advisory : GHSA-vphc-468g-8rfp NVD : https://nvd.nist.gov/vuln/detail/CVE-2026-33980...
pkgxray
pkgxray — pre-install security for npm packages, MCP servers, and AI agents Inspect an npm package or MCP server before you install or connect to it, and get a deterministic, evidence-backed SAFE, REVIEW, or BLOCK verdict. Local, zero-dependency static analysis — normal scans never execute packag...
CVE-2026-23744
CVE-2026-23744 Exploit to MCPJam Inspector Install libraries with: pip install -r requirements.txt - use python CVE-2026-23744 --help to info MCPJam inspector is the local-first development platform for MCP servers. The Latest version Versions 1.4.2 and earlier are vulnerable to remote code...
scopeblind-gateway
protect-mcp Local policy enforcement and signed decision receipts for AI agent tool calls. Developer page · Quickstart · Agent setup · Policy packs · Sample record · Integrations · Documentation · Contribute Put the gateway between an MCP client and its tool server, or use its hooks in a coding...
ghostsplice
GhostSplice: cross-channel trust fragmentation attack PoC Proof-of-concept code for GhostSplice , an attack from the ASSET Research Group. The full write-up is "The AI refused to steal the secrets. So we handed it a form.". The idea in plain words AI coding assistants like Cursor, VS Code with...
Gideon
██████╗ ██╗██████╗ ███████╗ ██████╗ ███╗ ██╗ ██╔════╝ ██║██╔══██╗██╔════╝██╔═══██╗████╗ ██║ ██║ ███╗██║██║ ██║█████╗ ██║ ██║██╔██╗ ██║ ██║ ██║██║██║ ██║██╔══╝ ██║ ██║██║╚██╗██║ ╚██████╔╝██║██████╔╝███████╗╚██████╔╝██║ ╚████║ ╚═════╝ ╚═╝╚═════╝ ╚══════╝ ╚═════╝ ╚═╝ ╚═══╝ Autonomous Cybersecurity...
promptfoo
Promptfoo: LLM evals & red teaming promptfoo is a CLI and library for evaluating and red-teaming LLM-based apps. Stop using trial-and-error... start shipping secure, reliable agents Website · Getting Started · Red Teaming · Documentation · Discord Promptfoo is now part of OpenAI. Promptfoo remain...
otto-support
Otto Support Customer support MCP server for AI coding assistants. One Go binary, tiered authentication, 19 tools across 4 role levels. Built with mcp-go. Quick Start Option A: Docker container recommended Run everything in an isolated container. Claude Code is pre-installed and the MCP server...
SkillsGuard
Support Development If SkillsGuard protects your pipeline, consider supporting ongoing research and new detection rules. ETH Donation Wallet 0x11282eE5726B3370c8B480e321b3B2aA13686582 Scan the QR code or copy the wallet address above. Static security scanner for AI agent skill packages. Detects...
hexstrike-ai
HexStrike AI MCP Agents v6.0 AI-Powered MCP Cybersecurity Automation Platform Advanced AI-powered penetration testing MCP framework with 150+ security tools and 12+ autonomous AI agents 📋 What's New • 🏗️ Architecture • 🚀 Installation • 🛠️ Features • 🤖 AI Agents • 📡 API Reference Follow Our Social...
masq
Sit where the model sits. See what it can see. MASQ MASQ is a local security CLI for AI agent stacks. It sits in the same seat the model sits in: it reads MCP tool catalogs, completes the MCP handshake, looks through session logs, and probes local model HTTP ports. Then it prints findings and...
agentsid-scanner
AgentsID Scanner The Lighthouse of agent security. Scan any MCP server. Get a security report card. Your MCP server exposes tools to AI agents. How secure is it? Most MCP servers ship with no authentication, no per-tool permissions, no input validation, and tool descriptions vulnerable to prompt...
lamda
FIRERPA Android | AI-Powered Automation An all-in-one Android automation framework that combines on-device services, AI-ready agents, and extensible tool invocation. Documentation | 使用文档 | TELEGRAM | QQ Group | SKILLS | llms-full.txt | 中文版本 FIRERPA is an all-in-one Android device control platform...
cve-mcp-server
🛡️ CVE MCP Server AI-powered security intelligence at your fingertips — 28 tools + a one-calltriagecve orchestrator, 24 data sources, one protocol. A production-grade Model Context Protocol MCP server that turns Claude into a full-spectrum security analyst. Instead of juggling 15+ browser tabs...
bouvet
Bouvet Isolated code execution sandboxes for AI agents About • How It Works • MCP Tools • Documentation What is Bouvet? Bouvet boo-veh is an MCP server that creates secure, isolated sandboxes for AI agents to execute code. When an AI agent needs to run Python, Node.js, or shell commands, Bouvet...
cortex
CORTEX v1.0.1 - INSTALLATION AND QUICK START Cortex v1.0.1 ships as a single portable Windows application: cortex.exe. The x64 and x86 instrumentation runtimes live in the runtime folder and are selected automatically for each target. Nothing else has to be installed no Qt, no Visual C++ runtime...
YourMemory
YourMemory Your AI has the memory of a goldfish. Not anymore. Persistent, self-improving memory for AI agents — built on the science of how humans remember. ▶ Try the live interactive demo · Website · Benchmarks The problem Every morning your AI agent treats you like a stranger. Same context...
CVE-2026-34200
Nhost MCP Server: One-Click Infrastructure Compromise Official Advisory: This vulnerability was acknowledged and published by Nhost: GHSA-6c5x-3h35-vvw2 This repository documents a vulnerability in the Nhost Local MCP Server. The service lacks inbound authentication and implements a permissive CO...
pocket_disasm
Pocket Disasm One MCP endpoint. Many isolated IDALib sessions. A lightweight, agent-first control layer for headless binary analysis with the IDA Pro MCP toolset. !IMPORTANT Pocket Disasm is an independent open-source project. It is not affiliated with, endorsed by, sponsored by, or an official...
tengu
Tengu — Pentesting MCP Server "In Japanese mythology, the Tengu is a fierce mountain spirit — master strategist, warrior, and trainer of samurai. In cybersecurity, it guides you through every phase of the hunt." From recon to report — AI-assisted pentesting in one command. Tengu is an MCP server...