Trentina

Overview

Trentina is a Model Context Protocol (MCP) server that acts as a secure gateway and quarantine system for AI agent traffic. It implements three-layer prompt injection defense to protect your AI workflows from malicious input and unauthorized access.

The server runs locally on your machine via the mcp-trentina-crunchtools package, installed with uvx mcp-trentina-crunchtools. It requires no credentials and operates over stdio, making it ready to use immediately after installation. Trentina is released under the AGPL-3.0 license with source code available at crunchtools/mcp-trentina on GitHub. The latest version is v0.5.0.

Trentina belongs in the AI & Agents category and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain Trentina, claim this listing to verify ownership and keep information accurate.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "trentina": {
      "command": "uvx",
      "args": [
        "mcp-trentina-crunchtools"
      ]
    }
  }
}