Add wundervault/wundervault-mcp to Security

README.md

@@ -3000,6 +3000,7 @@ Interact with Git repositories and version control platforms. Enables repository
 - [SPL-BGU/PlanningCopilot](https://github.com/SPL-BGU/PlanningCopilot) [![planning-copilot MCP server](https://glama.ai/mcp/servers/SPL-BGU/planning-copilot/badges/score.svg)](https://glama.ai/mcp/servers/SPL-BGU/planning-copilot) 🐍🏠 - A tool-augmented LLM system for the full PDDL planning pipeline, improving reliability without domain-specific training.
 - [yyyhy/nash-arena](https://github.com/yyyhy/nash-arena) [![yyyhy/nash-arena MCP server](https://glama.ai/mcp/servers/yyyhy/nash-arena/badges/score.svg)](https://glama.ai/mcp/servers/yyyhy/nash-arena) 🐍 ☁️ - A Chess and Card Game Arena For LLM, Agents can battle in game by mcp
 - [aarifmms/keyblind](https://github.com/aarifmms/keyblind) [![aarifmms/keyblind MCP server](https://glama.ai/mcp/servers/aarifmms/keyblind/badges/score.svg)](https://glama.ai/mcp/servers/aarifmms/keyblind) 📇 🏠 🍎 🪟 🐧 - Encrypted secrets vault with MCP for AI agents. Secrets resolved at runtime, never leaked to LLM conversations.
+- [wundervault/wundervault-mcp](https://github.com/wundervault/wundervault-mcp) 📇 ☁️ - Zero-knowledge secret vault for AI agents: use API keys, passwords, and SSH keys to run real commands (exec/rsync) with the secret injected into a single command — never returned to the model or shown in chat. Client-side AES-256-GCM, per-agent scoping, append-only audit log.
 ## Frameworks
 
 > [!NOTE]