Lightweight CWE-Mapped Pre-Audit Security Scanner & Agent Skill for MCP Servers, Agent Hooks, and Firebase Rules — Scientist HM Shihabuddin Jashory (Vision Flow Group)
Security, schema and token-cost checks for MCP servers and AI agent tools. Static analysis that never runs your code, with policy gates for CI, SARIF, and a deliberate 'n/a' when a scan could not read
Model Context Protocol (MCP) server for Sophos Firewall (SFOS) appliances with fastembed semantic tool routing and IBM ContextForge Gateway support.
MCP Server for Ghidra Last Updates
MCP server for Greenbone Vulnerability Management, communicates with rust-gvm-api.
Stops AI coding agents from installing or running npm packages that don't exist. Claude Code plugin + MCP server, zero deps, no account.
Sovereign AI-Native Linux OS powered by Linux 7.3.0 Rust Kernel, autonomous agent runtime (Mr. Flow), 320+ clean-room reverse-engineering tools & rolling OTA.
MCP server for Pi-hole v6 API — supports multiple instances
The Zero-Trust Safety & Settlement Rail for Autonomous AI Agents. Sub-10ms deterministic guardrails, key leak defense, and cryptographic Proof-of-Safety attestations via x402 on Base ($0.002).
Secure read-only PostgreSQL MCP server in Rust — a hardened alternative to the deprecated @modelcontextprotocol/server-postgres.
Multi-account Claude Code usage monitor & silent account switcher, plus a Slack/ClickUp MCP server — macOS menu bar + CLI. Local-first, no telemetry.
实现带鉴权的Spring AI MCP 服务,并通过Spring AI/Langchain4j/Cherry Studio进行调用
One searchable history across every AI coding tool, with secret scanning and a shared task board.
AetherScope V2 — SAST 3D WebGL & Serveur MCP (Claude/Antigravity/Cursor). Détection de 150+ CWE & Zero-Day Patterns (Rust, C++, PHP, Node.js, Web3), contrats EARS BLAKE3 et PoC Bug Bounty.
Upgrade intelligence for AI agents: what an upgrade changes, where it touches your code, CVE scans.
Cognitive digital twins and behavioral modeling for AI agents.
enterprise grade mcp security
Query OSV.dev for package vulnerabilities and batch-audit dependency lists via MCP.
MCP server for AI-driven penetration testing. Wraps 22 security tools (nmap, nuclei, sqlmap, Metasploit…) as 46 safety-hardened MCP tools for Claude and LLM agents. Written in Rust.
GhidraMCP fork (MCP server + Ghidra plugin) with a server-side run_python tool for bulk Ghidra reverse-engineering ops. Renamed to coexist with upstream; default port 8765.
Static analysis for AI and agent code: Python, TypeScript, JavaScript, MCP manifests and live servers, Skills, and dependency CVEs.
AI security testing — find security vulnerabilities in LLM apps, chatbots, AI agents, MCP servers, and RAG systems. Mapped to OWASP (LLM, Agentic, MCP) and NIST AI RMF.
A shield against reverse-engineering tactics — including REA — for your own shipped JavaScript. Moves secrets server-side, seals crown jewels, collapses the module graph. Raises cost and defeats most
MCP Oauth Proxy acts as an proxy authorization server to use enterprise managed authorization for MCP and A2A use cases
Search 1,032 verified smart contract vulnerability findings from Sherlock audits by pattern.
Neuro-Symbolic Law-to-AST Compiler, Microsoft Z3 Formal Verifier, 12-MCP Suite, Contextual+Graph RAG, and Autonomous PR Enforcer (JusticeSphere AI / ComplianceOS)
Lightweight MCP server for deterministic CVSS Base Score calculation, supporting CVSS 2.0, 3.0, 3.1, and 4.0.
A framework for building and running your own living GenAI/LLM threat model. Ships with a curated reference catalog, an LLM-driven assessor, and an MCP server
BurpMCP - Enables Claude Code CLI to orchestrate Burp Suite through MCP server
Reusable standalone MCP JSON-RPC/HTTP server for Burp extensions
Security scanner for AI agents. Finds vulnerabilities in MCP servers, agent configs, and tool setups. Written in Rust.
Provider-neutral OAuth 2.1 authorization broker for MCP, with Python, Go and TypeScript resource-server SDKs.
MCP server for Interlynk API. This server enables AI assistants like Claude, Cursor, and VS Code Copilot to interact with your Lynk organization for SBOM management, vulnerability tracking, and compli
Reverse engineering and implementing the Minecraft server protocol in Go
The numbers No Man's Sky doesn't show you: refining, cooking, crafting, nanites, storage and portal addresses, read from the game files. As a web app (nmsii.dlu.one), a terminal app (Textual TUI), an
Security scan for AI-generated code: injection, SSRF, secrets, weak crypto, unsafe deserialization.
完整目錄
IAM、掃描與機密管理。共 1,350 個伺服器,最常用的排在前面。每個都會開啟發布者的頁面。