Security & Testing MCP Servers for Claude Desktop

Vet third-party AI agent extensions + agent-config files (AGENTS.md, .cursor/rules, CLAUDE.md).

Who can change a Solana program or EVM contract, dependency advisories, scans. Paid per call (x402).

Package risk checks: maintenance, licence, advisories. Paid per call in USDC, no signup.

Catches hallucinated and slopsquatted npm and PyPI packages before an agent installs them.

Real-time threat intelligence lookups and IOC parsing from your self-hosted Polarity instance.

Sign AI output for EU AI Act + FRE 902 compliance, verify content authenticity provenance

Symbiotic CLI MCP Server for security scanning and analysis

Coverage analysis, untested function detection and complexity scoring for TS and JS.

Drive the iOS Simulator from an agent: read the screen, tap/type/swipe, replay flows in CI.

GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection

Synthetic time-series test data with trend, seasonality, noise, and anomalies, for any MCP client.

AI agent governance for MCP: PII detection, policy enforcement, compliance, and kill switch.

Open-source MCP server for WhisperGraph - query the internet's infrastructure & threat-intel graph (DNS, BGP, GeoIP, WHOIS) via Cypher.

Multi-agent LLM security layer detecting prompt injection and jailbreaks.

MCP server that converts test failures into Jira-ready defect reports — inside any MCP Client, no LLM API key needed.

Playwright & Appium test automation for Claude. Generate tests, diagnose failures, open fix PRs.

OSINT sweep of a digital footprint: breaches, accounts, data brokers, domains and IPs

MCP server bridge for Codex app-server

This is a Crawler Security Guard based on the Model Context Protocol (MCP).

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

Visual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.