Trust

Overview

Trust is a Model Context Protocol server that provides a security and identity layer for AI agents. It enables identity verification, content guarding, data redaction, escrow services, and x402 payment handling—all exposed as tools your AI assistant can invoke directly.

The server runs locally via the npm package @agntor/mcp, communicating over stdio on your machine. It requires an API Key for authentication and is distributed under the MIT license at v0.1.0. The source code is available at agntor/mcp on GitHub.

Trust appears in the AI & Agents category and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you maintain Trust for agntor, claim this listing to verify ownership and keep the information current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "trust": {
      "command": "npx",
      "args": [
        "-y",
        "@agntor/mcp"
      ]
    }
  }
}