Security & Testing MCP Servers for Claude Code

Eu Ai Act Compliance MCP Server by MEOK AI Labs

NYC Local Law 144 AEDT bias audit — selection rate, impact ratio (4/5ths), public summary

Cortex observable-analysis control CLI with an MCP adapter

Third-party cryptographic proof for AI agent API calls — ArkForge Trust Layer MCP server

AI-powered E2E testing MCP server. Detects and auto-fixes UI bugs via DevQA Loop and Vision AI.

Zero-egress PII redaction for Claude. Runs locally — no data leaves your infrastructure.

VIGIL is a safety and compliance oversight layer for AI agents that produces verifiable compliance receipts: check risky actions before

Tamper-evident audit trails for AI agents — Ed25519-signed, hash-chained, EU AI Act ready.

A 1:1 replica of Claude Desktop's computer-use tool surface, for Windows and the Claude Code CLI.

Local encryption and project setup plugin for Copass. Keys never leave your machine.

Servidor MCP para consultar el ENS y mantener declaraciones de aplicabilidad auditables.

EU AI Act Article 5(1)(f) gambling-vertical compliance audit MCP. Detects AI systems that exploit ps

Automated EU AI Act Annex III risk classification and impact assessment engine

MCP proxy for AI parental controls — content guardrails, spiral detection, parent notifications via Telegram/iMessage/WhatsApp

Secure local MCP bridge for ChatGPT and local agents, with workspace-scoped task loops, safe summaries, audits, and Direct editing.

Security for AI agents: MCP audits, secret redaction, skill vetting, network scans, agent checkout.

MCP server for SolidityScan smart contract security analysis

MCP server for Supabase security: audit (with active anon-key probe that proves leaks live), dry-run fixes, and apply remediations with

Scans self-hosted multi-tenant AI-agent platforms for tenant-isolation gaps via an MCP tool.

MCP server for the Vectra AI Platform - exposes detection, investigation, and response tools to AI assistants.

Execution-grounded verification for AI coding agents on Windows: evidence, not agent claims.