SkillAvatars
Model Context Protocol servers - tools, resources, and prompts for Claude and other AI assistants.
Start Better
MCP discovery works better when people begin from a job to be done. Route them into a scene, a curated stack, or a high-signal tag before they start scanning tool cards.
Scenes
Stacks
Popular tags
Showing 24 of 286 MCP tools
📣 ANNOUNCEMENT: The Openapi® OAuth system just got a major upgrade V2.
The foundational MCP/A2A-native secure credential injection + x402 micropayment gateway for the agent economy. Building the open infrastructure layer that autonomous agents actually need.
The Governed Agentic AI Operating System — 65 Rust crates, 658 commands, 84 pages, 5,029 tests, 10/10 OWASP
Persistent memory for AI agents — save and search knowledge across sessions via MCP. Local-first, markdown + SQLite + embeddings.
Read-only MCP server for Charles Schwab Market Data Production API (14 tools, OAuth, DuckDB cache, OWASP-tested).
Scans Model Context Protocol (MCP) server configurations for common security issues: overprivileged tools, missing auth, prompt injection surface, unsafe defaults.
🔴 Elevate your security skills with hands-on training in red teaming for GenAI and AI/ML systems, focusing on adversarial techniques and vulnerabilities.
Agentic bug bounty and pentest orchestrator. Claude Code plugin. Phase-aligned playbooks (recon -> scan -> manual -> chain -> report), parallel sub-agent dispatch, Kali via kali-ssh MCP.
MCP server giving Claude Code 51 typed SSH tools across your server fleet. Pooled, gated, context-lean — stop being the middleman.
🛠️ Curate and enhance your coding skills with Claude Skills Vault, a collection of commands and MCP server guides for efficient development.
Security, cost, and health governance proxy for MCP infrastructure — YAML policy engine, OAuth 2.1/OIDC, web dashboard, mTLS, semantic shell analysis, STRIDE threat model
Connect any MCP client to your Synology NAS. Browse, search, and manage files, monitor system health, with 2FA support and permission-tiered access control.
MCP server for Obsidian vaults — plugin-free search, memory, link graph, and full vault access for any AI agent. Local or fully remote: one Docker container, Streamable HTTP, OAuth 2.1.
Security, cost, and health governance proxy for MCP infrastructure — YAML policy engine, OAuth 2.1/OIDC, web dashboard, mTLS, semantic shell analysis, STRIDE threat model
Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-aware, author-independent, and shift-left: secure_prompt secures the prompt before code generation. The security MCP for vibe coding: 442 rules, 38 tools, CLI + doctor for Next.js, Supabase, Clerk, Stripe, Prisma, Hono & MCP.
Restore Claude access in OpenCode with OAuth for Pro/Max logins, token refresh, and Anthropic model support
ESLint security rules for MCP servers — catches SANDWORM_MODE credential harvesting, path traversal, command injection, and CVE patterns at dev time
LLM Security Red Teaming Tool 2026 - 80+ Attack Plugins, 25+ Mutation Strategies for AI
Comprehensive Better Auth MCP Server with complete documentation and configuration tools
Credential-governance proxy for AI agents (OpenClaw, Hermes). MCP gateway + SOCKS5 proxy with Telegram approval, phantom token injection, all-protocol DLP, and tamper-evident audit.
Safe SSH MCP Server for running commands over SSH
Manage ESP32 factory setup with auto certs, Wi‑Fi AP config, OTA updates, and Let’s Encrypt support in a <1MB image
Claude Code skill for comprehensive security auditing of GitHub repositories — specialized for AI agents, Skills, and MCPs
Persistent SSH PTY session manager for MCP clients with actor-aware input tracking, split dashboard rendering, and automatic session cleanup. | https://zw-awa.github.io/ssh-session-mcp/