Security & Testing MCP Servers for ChatGPT

Local stdio MCP server (and CLI) that audits a software project against the UK ICO Age Appropriate Design Code (the Children's Code). Runs

An MCP server that captures Android emulator/device screenshots for AI agent visual analysis

MCP server for Applied Operations Protocols — agent-executable compliance documentation for the Colorado AI Act and operational standards

Read-only tools for AI agents: who can change a smart contract, how fast. Signed data, testnet.

An open-source MCP server that verifies C2PA content credentials and returns LLM-ready provenance verdicts. Built by c2paviewer.com.

An MCP server that provides tools to author OSCAL security compliance documentation

MCP Server for Conviso Platform integration

Kill switch + spend guard for AI agents that spend money, across every wallet vendor at once.

Model Context Protocol (MCP) server wrapping the public CTFtime API - query CTF events, teams, rankings, and results

MCP Server for Dependency Track API

MCP server for real-time dependency security — checks packages against CVE databases before your AI coding agent installs them. Works with

MCP server exposing Detox mobile E2E workflows to Claude Code

MCP server that classifies AI systems under the EU AI Act (Regulation (EU) 2024/1689) — risk tier, obligations, deadlines, EUR-Lex

Agent-grade document production MCP server powered by Typst

Local stdio MCP server for Dynamic Feed — live data AI models lack (prices, weather, CVEs & exploited vulns, internet outages, global

Model Context Protocol (MCP) server for ESET PROTECT (On-Prem & Cloud) — manage devices, policies, detections, incidents, quarantine, and

Transparent rule-based GitHub fake-star detector — LOW/MEDIUM/HIGH with per-rule evidence.

Security scanner for AI agents — detect threats in MCP servers, Claude skills, Codex plugins, Cursor extensions, and 5 more platforms. 227

The Vault Protocol - Cryptographic containment and capability management for AI agents

Model Context Protocol bridge for interactsh

Prove that a code change actually works, whether an agent wrote it or a pull request did.