Vaults and credentials.
A lightweight utility that securely loads API keys for Cursor MCP servers from your home directory, preventing accidental exposure of secrets in repositories. Keep your credentials safe while maintaining seamless integration with AI coding assistants.
CTRL_ — security audit MCP server for AI-generated Next.js, Vite and Express apps. Finds exposed keys, unsafe queries and open row-level security, then walks your coding agent through fixing them. Extra depth on Supabase.
MCP server — save, search, and retrieve reusable code snippets via Claude
MCP server that gives AI agents persistent memory across sessions. Context recall, encrypted credentials, session notes, export/import — zero external requests.
Security linter for environment variables, Docker, CI, Kubernetes, and runtime configuration.
Wall data reader + self-hosted MCP server (single binary). Reads Wall export ZIPs and serves them locally for personal viewing, search, and LLM access.
Scan any MCP server for prompt injection, tool poisoning, leaked secrets, and destructive capabilities. One command, no key, no signup.
Security scanner for MCP servers. Find vulnerabilities before your AI agent does.
Install Seatbelt MCP + /seatbelt skill (npx withseatbelt)
Second Brain Lite (MCP) — connect any MCP-compatible assistant to your Obsidian vault
One source of truth for your MCP servers — fold one config out to every client.
Open source, end-to-end encrypted context vault for developers who use several AI tools. Local MCP server + CLI.
VibeSecurity — Auditoria de segurança para quem cria com IA. Secrets, vulnerabilidades e rotas sem auth.
Compliance & data-integrity for AI agents: sanctions/watchlist screening (10 official lists — OFAC SDN+Consolidated, UN, EU, UK OFSI, Canada, Australia, France, Switzerland, US SAM exclusions — ~229k parties, daily), one-call KYB, identifier validation, FATF+EU jurisdiction risk, PII/secret detecti…
Outcome-first fallback for autonomous agents, bots and AI. When a toolchain cannot finish a task, state the desired result; HumanMirror discovers the smallest live capability, exposes cost before paid execution, and returns deterministic machine-readable results and verification.
Read-only MCP over a vault's typed knowledge graph: concept search, contradictions, article fetch.
HSM-backed secret management and multi-chain transaction signing for AI agents. Store secrets, sign transactions, and proxy LLM traffic through a Trusted Execution Environment.
Local-first secret scanning, rotation, vault, and audit-log tools for AI agents.
Consent-scoped vault access and free verification of family-issued learning records.