Search

MCP server package - Created by Poneglyph for security research

Native macOS menu-bar app connecting ChatGPT to one scoped local folder through Secure MCP Tunnel and 65 MCP tools.

Library to turn your app's database into an MCP server for coding agents (Claude Code) — adapter-agnostic, row-level security, zero SQL

One-command elite security setup for Claude Code CLI: 56 skills, 26 agents, 16 commands, 10 MCP servers

Japanese prompt injection detection and x402 pre-payment security check API. Deterministic validator included. No AI used for core validation.

AegisMCP Enterprise is a dual-layer security gateway and cost firewall designed to sit between AI models (like Claude and Cursor) and execution engines.

Drug shortage intelligence: GraphRAG over FDA data, multi-tenant RAG with row-level security, LangGraph memo agent, MCP server

Library to turn your app's database into an MCP server for coding agents (Claude Code) — adapter-agnostic, row-level security, zero SQL

MCP server for SailPoint Identity Security Cloud (ISC) Transform authoring — scaffold, strict lint, catalog, and safe upsert to live tenants.

Typed Python client for the Korea Investment & Securities (KIS) Open API — quotes, orders, accounts, real-time, CLI, and an optional MCP server.

ChatGPT thinks. Codex works. A local-first MCP bridge for multi-project Codex Desktop sessions, confirmed execution, and secure ChatGPT control.

Security scanner for Claude Code skills and MCP servers. Detects prompt injections, hidden Unicode attacks, credential harvesting, and supply chain risks before installation.

Hands-on AI & LLM security labs. Attack and defend agentic AI systems, MCP servers, and LLM applications. OWASP Agentic Top 10 mapped.

A secure second brain for people and their agents. Shared context across Claude, ChatGPT and Cursor: agents propose, people approve, and secrets never reach a model.

🛡️ A Model Context Protocol (MCP) server for AI security: detects prompt injection, masks sensitive data (PII), and audits insecure MCP configs.

A security-hardened MCP server for managing Technitium DNS Server via its HTTP API, offering tools for DNS zones, records, blocking, cache, settings, and diagnostics.

Security scanner for repos, apps, and things built with Claude (skills, plugins, MCP servers). Runs as a Claude Code skill. 332 checks, 4 scan modes.

Software supply chain security MCP server — vulnerability scanning, package analysis, provenance verification, typosquatting detection, dependency intelligence across npm, PyPI, crates.io, Go, and more

A multi‑agent security copilot that inventories MCP servers/tools, correlates them with vulnerability intelligence, and tests for prompt‑injection/tool‑misuse paths—producing an auditable “agentic attack surface report”

Claude skills for security governance, compliance framework mapping, FAIR risk quantification, and executive reporting - with optional MCP server integrations for NIST CSF, SOC 2, ISO 27001 and more frameworks.