diff --git a/README.md b/README.md
index 8bc1f4919..1c0b19dd5 100644
--- a/README.md
+++ b/README.md
@@ -4098,6 +4098,8 @@ Tools for conducting research, surveys, interviews, and data collection.
 
 - [gostanos/smallprint-action](https://github.com/gostanos/smallprint-action/tree/main/mcp) [![gostanos/smallprint-action MCP server](https://glama.ai/mcp/servers/gostanos/smallprint-action/badges/score.svg)](https://glama.ai/mcp/servers/gostanos/smallprint-action) 📇 ☁️ - Read the Small Print record: the tool descriptions, schemas and instructions of MCP servers, agent skills and plugins, hashed every version and diffed between releases, each change graded by a printed rule, with public advisories joined by version. Four read-only tools over the public record, including a yes-or-no check that a server's small print has not moved since the version you approved; `npx -y smallprint-mcp`.
 
+- [aurelio-nakamura/cmdxray](https://github.com/aurelio-nakamura/cmdxray) [![aurelio-nakamura/cmdxray MCP server](https://glama.ai/mcp/servers/aurelio-nakamura/cmdxray/badges/score.svg)](https://glama.ai/mcp/servers/aurelio-nakamura/cmdxray) 📇 🏠 🍎 🪟 🐧 - A safety gate and explainer for AI coding agents that run shell commands. `check_command_safety` returns a danger/caution/none verdict for a proposed command — catching `rm -rf /`, `curl | sudo bash`, `dd`/`mkfs`/`shred` to a device, `chmod -R 777 /`, fork bombs, `git push --force` and CI `${{ }}` script-injection — so an agent can guard a command before executing it. `explain_command` gives a token-by-token breakdown of every flag, pipe, redirect and subshell. Fully offline, zero dependencies, nothing leaves the machine. `npx -y cmdxray mcp`.
+
 ### 🌐 <a name="social-media"></a>Social Media
 
 Integration with social media platforms to allow posting, analytics, and interaction management. Enables AI-driven automation for social presence.