17 skills found
AuthPlane / authserverOAuth 2.1 Authorization Server for the Model Context Protocol (MCP)
jazzmind / 003-zero-trust-authenticationA self-hosted AI platform that keeps your data on your infrastructure. Busibox integrates document processing, semantic search, AI agents, and custom applications into a single platform — running on Docker with enterprise-grade security baked in. Think of it as a Linux distribution for AI.
localden / mcp-auth-servers🔒 Reference MCP servers that demo how authentication works with the current Model Context Protocol spec.
mostaffa / FastAPI-RBACA modern, production-ready Role-Based Access Control (RBAC) system built with FastAPI
abluva / mcp-remoteThe bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability
casdoor / casdoorAn open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD
radumalica / infrastructure-mcpGive Claude Code, Cursor, and other AI agents safe access to your real infrastructure — without giving them raw SSH access.
assinafy / mcp-serverMCP Server for the Assinafy digital signature API. A digital signature platform for Brazil.
Cyreslab-AI / shodan-mcp-serverA Model Context Protocol server that provides access to Shodan API functionality
evansims / openfga-mcpModel Context Protocol server enabling querying and management of OpenFGA and Auth0 FGA authorization stores for automation, intelligent tooling, and natural language.
WellApp-ai / connectConnect and verify the Well MCP — authenticate, confirm the tools work, and show what to ask
AgentsID-dev / agentsid-scannerSecurity scanner for MCP servers. Grades auth, permissions, injection risks, and tool safety. The Lighthouse of agent security.
openclaw / 1passwordSet up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
PatrickJS / nextjs15-supabase-cursorrules-prompt-file27 architecture rules preventing AI hallucinations: insecure auth (getSession vs getUser), synchronous params, deprecated imports, missing RLS, and Stripe key exposure. Built for Cursor Agent and Claude Code.
ok-helloworld / vibe-pentestVibe Pentest（AI 渗透测试）是一款基于 AI Agent 架构的自动化渗透测试工具，采用多 Agent 并行执行架构，能够对 Web 应用、API、管理后台等进行全面的黑盒渗透测试（包括业务逻辑漏洞评估），输出稳定可靠的安全报告，并提供可落地的整改建议。
opslane / opslaneVerification Layer for Claude Code
bridge-mind / BridgeWardTrust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.
