Security & Testing MCP Servers for Claude Desktop

A cross-platform TUI/CLI/API/MCP command library for authorized security testing.

Security tools for AI coding agents.

Scan a blob of code/text/diff for LEAKED SECRETS before you commit or share — API keys (AWS, GitHub, OpenAI, Stripe, Google, Slack…)

Local-first privacy MCP server for sensitive AI workflows

Live web health & security check for any domain or URL, as an MCP tool and a pay-per-call x402 endpoint. Does a real TLS handshake to grade

MCP server that lets LLMs drive ActionTestScript (ATS) — test automation across web, mobile, desktop, and API, powered by ats-core's REPL.

MCP server for auditing AWS AI/ML workload security — Bedrock IAM, prompt injection signals, posture reports

MCP server for ClawGuard Shield — scan AI agent inputs for prompt injection threats

A minimalistic MCP client for testing MCP Server

Centralized security instruction server for AI-assisted code generation

AI Compliance Calendar MCP server — track AI regulations, deadlines, risk assessments, and policy updates across jurisdictions (EU, US, UK

Lite Model Context Protocol server for comprehensive CVE intelligence gathering with multi-source exploit discovery, designed for security

Model Context Protocol server for deny.sh deniable encryption. Lets any MCP-compatible AI agent call deny.sh tools.

Agent Governance Gateway — bounded, auditable, session-aware control for AI agents with MCP proxy, shell proxy, and HTTP API

Security gateway for Model Context Protocol servers: policy enforcement, secret redaction, prompt-injection screening, tool rug-pull

MCP server for fraud prevention — IP reputation, email breach detection, URL safety, phone validation and risk scoring via free APIs

Model Context Protocol server for FutureVuls vulnerability management service integration (Office Environment with Proxy Support)

Deception middleware for AI agents - detecting data theft and indirect prompt injection in MCP servers

Safety checks an agent runs before it acts: package malware, destructive command, secret leak.

Read-only MCP server over a local log-analysis backend; a client that computes no verdicts.

Official Model Context Protocol (MCP) server for Kaminari Click — traffic-quality statistics, saved reports, shared reports, and IP/UA