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.
Scan GitHub repos and profiles for malware before you clone — CLI and MCP server for the Flagrix scanner
Local-first security check MCP server for AI coding agents — finds hardcoded secrets, exposed .env files, secrets in git history, and vulnerable dependencies in your workspace, entirely on your machine.
Heimdall — a security scanner for Model Context Protocol (MCP) servers. Vet a server, or a whole agent config, before your agent trusts it.
MCP server that finds Korean e-Gov/finance sites and opens them in a clean, disposable Windows Sandbox with the required security software. Discovery + safe-launch only (no RPA). Node/TS implementation (counterpart of the .NET dnx build). Dual-licensed: A
Postgres Editor with Guardrails
The open source standard for secure, private AI: a wall the operating system enforces in both directions, and your data under your own keys, portable anywhere. Any agent, local or cloud, solo or fleet.
MCP server for authoring Maltego graph files and running primitive OSINT lookups.
An MCP server enabling LLMs to write integration tests through live test environment interaction
Model Context Protocol server exposing Fracta scan tools (passive_scan, scan_repo, …)
Official MCP server for Autousers — UX evaluation, calibrated AI personas, side-by-side design review.
Security scanner for MCP (Model Context Protocol) servers. Detect vulnerabilities, secrets, injection risks, and misconfigurations before deployment.
Unofficial MCP server that integrates with the Proton Pass CLI
The Judge Protocol - Thread identity, intent verification, and blockchain anchoring
MCP server to check dependencies against OSV.dev and Socket.dev
AI-driven mobile app testing via MCP — any AI agent can test any Android app
AtlaSent MCP server — authorize-before-execute for any MCP-compatible AI agent
The Vault Protocol - Cryptographic containment and capability management for AI agents
MCP server for the perfscale OSS CLI: run load tests, lint and manage test/config YAML locally
Fail-closed stdio firewall for risky local MCP JSON-RPC tool calls
Trust scoring for AI agents. Investigate, verify, and compare agent trustworthiness through MCP.
Portable, enforced agent personas. One spec - any runtime.
gRPC and connect RPC mock server with hot reload, and rule-based responses
ESLint security rules for Model Context Protocol (MCP) servers — catches SANDWORM_MODE credential harvesting, path traversal, command injection, and CVE patterns at dev time
Security scanner for MCP (Model Context Protocol) servers. Detect authentication gaps, credential exposure, SSRF risks, and misconfigurations. Maps findings to OWASP MCP Top 10.