MCP servers for security scanning, vulnerability testing, secrets management and QA automation. Each entry is scanned with the deterministic Capability-Flow Trust Model — grades are computed, never self-reported.
The bidirectional firewall for MCP — scans inputs AND outputs, detects rug-pulls at runtime, zero config.
CLI toolkit for provisioning, securing, and managing self-hosted servers
A secure MCP CLI server implementation with comprehensive path whitelist validation, providing controlled file system operations and command execution in a protected environment. Features include strict security measures, real-time path validation, secure
MCP server for controlling Android emulators via ADB
Advanced MCP server for security detections with Detection Engineering Intelligence, Knowledge Graph (Tribal Knowledge), Elicitation, and Resource Subscriptions
Model Context Protocol server exposing a BVCC Agent Wallet to AI runtimes (Claude Code, Cursor, Claude app). Tools are generated from the @bvcc/agent-sdk capability catalog.
Agent-first MCP server for WeChat Mini Program debugging, automation, and lightweight testing
MCP server for MobAI - AI-powered mobile device automation
MCP plugin to control Android devices via ADB for automation, testing, and agent integration
Advanced Model Context Protocol (MCP) server for Vitest testing with intelligent resources, coverage analysis, and AI-assisted development workflows
MCP server that scans other MCP servers for prompt injection, data exfiltration, and privilege escalation. Add to your .mcp.json and let your AI agent audit its own tools.
Account-free MCP server: catch AI-hallucinated packages (npm, PyPI, crates.io, RubyGems, Go, Packagist), risk-score the dependencies an AI agent introduces, and find hardcoded secrets before you commit. Exposes the free pre_flight_check tool over stdio.
Mission Trust Graduation gate for Claude Desktop. Claude can do more for you once Mission decides what it's allowed to do.
Software supply chain security MCP server — vulnerability scanning, package analysis, provenance verification, typosquatting detection, dependency intelligence across npm, PyPI, crates.io, Go, and more
MCP server for testing Electron apps via Playwright - supports both CDP connection and direct launch
MCP server for Blacksmith CI analytics
AI-powered app test automation MCP server - scenario generation, execution, detection, and auto-fixing
HAL (HTTP API Layer) - An MCP server that provides HTTP API capabilities to Large Language Models with OpenAPI/Swagger integration
Advanced Zebrunner MCP Server — analytics, reporting, and safe mutations for Zebrunner. Complements the official Zebrunner MCP (beta). Tools registered as adv_<name> with legacy aliases kept for backward compatibility.
Free, real-browser accessibility scanner for AI coding agents. Scans localhost with Playwright + axe-core (and optionally Pa11y/HTMLCS), returns WCAG 2.1 Level A + AA violations with fix plans.
Core MCP server for Electron Stagewright. Drive Electron apps the way Playwright drives browsers.
Cryptographic audit trail for AI agents — sign, chain-verify and export every decision. GDPR / HIPAA / EU AI Act ready. Free & open source.
MCP server that gives AI coding assistants (Claude, Cursor, Windsurf) the ability to see and interact with Android mobile devices via ADB — AI-powered visual inspection, element finding, and device automation
MCP (Model Context Protocol) server for leakferret. Stops AI agents from committing live secrets.