diff --git a/README.md b/README.md
index 5c44d8313..a8e74e487 100644
--- a/README.md
+++ b/README.md
@@ -4353,6 +4353,7 @@ Interact with Git repositories and version control platforms. Enables repository
 - [FastMCP](https://github.com/jlowin/fastmcp) 🐍 - A high-level framework for building MCP servers in Python
 - [jamjet-labs/jamjet](https://github.com/jamjet-labs/jamjet) [![jamjet-labs/jamjet MCP server](https://glama.ai/mcp/servers/jamjet-labs/jamjet/badges/score.svg)](https://glama.ai/mcp/servers/jamjet-labs/jamjet) 🦀 🐍 - Durable, agent-native AI runtime with native MCP client + server and A2A support. Rust core for performance, Python authoring for ergonomics. Features graph-based workflows, durable execution, and multi-agent coordination.
 - [FastMCP](https://github.com/punkpeye/fastmcp) 📇 - A high-level framework for building MCP servers in TypeScript
+- [alexar76/warden](https://github.com/alexar76/warden) [![alexar76/warden MCP server](https://glama.ai/mcp/servers/alexar76/warden/badges/score.svg)](https://glama.ai/mcp/servers/alexar76/warden) 📇 🏠 🍎 🪟 🐧 - **WARDEN** — MCP security firewall (library + stdio scanner): static tool-def scan → signed threat feed → origin → pinning before third-party tools reach the model. Zero npm runtime deps. `npx -y @aimarket/warden`. [landing](https://warden.modelmarket.dev/) · [field survey of 1,108 public MCP servers](https://github.com/alexar76/warden/blob/main/docs/mcp-survey.md)
 - [ljppanda/mcp-longjobs](https://github.com/ljppanda/mcp-longjobs) [![ljppanda/mcp-longjobs MCP server](https://glama.ai/mcp/servers/ljppanda/mcp-longjobs/badges/score.svg)](https://glama.ai/mcp/servers/ljppanda/mcp-longjobs) 📇 🏠 🍎 🪟 🐧 - Durable, resumable operations for MCP servers via a client-agnostic facade: background tool execution with progress polling, mid-flight input, cooperative cancellation, plus chunked file transfers with resume cursors and sha256 verification. Works on every MCP client today — no Tasks-extension support required.
 - [SonAIengine/graph-tool-call](https://github.com/SonAIengine/graph-tool-call) [![graph-tool-call MCP server](https://glama.ai/mcp/servers/SonAIengine/graph-tool-call/badges/score.svg)](https://glama.ai/mcp/servers/SonAIengine/graph-tool-call) 🐍 🏠 - When tool count exceeds LLM context limits, accuracy collapses (248 tools → 12%). graph-tool-call builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy to 82% with 79% fewer tokens. Zero dependencies. Also works as an MCP Proxy — aggregate multiple MCP servers behind 3 meta-tools.
 - [vinkius-labs/mcp-fusion](https://github.com/vinkius-labs/mcp-fusion) 📇 [![Glama](https://glama.ai/mcp/servers/badge/@vinkius-labs/mcp-fusion)](https://glama.ai/mcp/servers/@vinkius-labs/mcp-fusion) - A TypeScript framework for building production-ready MCP servers with automatic tool discovery, multi-transport support (stdio/SSE/HTTP), built-in validation, and zero-config setup.