Security

The mcp-auth command: log in to a SAP BTP or ABAP destination and write it — its means and the secret the login obtained — through @mcp-abap-adt/auth-broker

Cross-agent permission policy specification for AI coding agents

Merged agent permission rules: which settings file wins, and which rules your client ignores.

Create-only, age-encrypted deposits of new logins and notes into Vaultwarden, without vault reads.

MCP server for CPFHub.io. Query Brazilian CPF data directly from AI agents.

Fix 'Dynamic Client Registration rejected (HTTP 403)' when connecting a non-catalog MCP client to Figma's remote MCP server. Mints an OAuth token via the allow-listed Codex CLI and injects it into your agent's MCP config as a Bearer header.

Capture a web page from your own Chrome as a PDF whose text is still text.

Tool-level authorization for Model Context Protocol servers: Better IAM credentials, agents and OAuth tokens.

Turn your existing app into an OAuth 2.1-protected MCP server. Bring your own identity, tools and storage; users connect Claude, ChatGPT, Cursor or any MCP client to their own data.

Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.

Build your own MCP server from plugins. Auth (API keys, OAuth), per-user permissions, audit log, SQLite or Supabase state, and built-in Google Drive, Slack, GitHub and Railway connectors.

Verified AI development. Scan your project, generate context, verify every change through a five-agent pipeline.

A calibrated firewall for AI agent tool calls: screens them before they run, and screens tool results before the agent reads them. Covers MCP servers through a proxy and a client's built-in tools through a hooks adapter.

25 expert React Native agents — upgrades and New Architecture migration, debugging, animation and gestures, performance, security, offline sync, navigation and deep linking, push notifications, permissions, iOS/Android parity, state management, accessibil

High-performance zero-dependency static analysis tool enforcing NASA Power of Ten rules across 20 programming languages, plus AI agent skill, MCP server config, prompt template, and LLM model security auditing.

SmartGuard MCP Server - AI-powered smart contract security audit tools for Claude Code, Cursor,...

HeartFlow (心虫) — AGI Layer 1: the Discriminator. Rule-based engine that checks what AI says before it reaches humans. 46 discrimination dimensions, 9-layer pipeline, 137 modules (logic/decision/cognition/emotion/memory/ethics/collaboration), 179 MCP tools

Agentic OS MCP Server — 150+ tools with on-demand loading (26 core), Streamable HTTP transport, background task engine, browser automation, TF-IDF semantic memory, multi-agent orchestration. Zero API keys.

Encrypted secrets and credential management for agents

Browser automation using Playwright with optional stealth mode to bypass anti-bot protection.