Lotor

Overview

Lotor is a Model Context Protocol server that acts as a local receipt and approval gate for AI agent sessions. It lets agents take action while maintaining human control over signing and final authorization. By implementing MCP, Lotor integrates directly with AI assistants as callable tools, eliminating manual copy-paste workflows between applications.

The server runs entirely on your local machine through the npm package lotor-mcp, communicating over stdio with no external credentials or setup required. Version v1.0.2 is available now under the Apache-2.0 license, with source code hosted at githubscum/lotor on GitHub.

Lotor belongs in the AI & Agents category on mcp.site and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. Maintainers are invited to claim this listing to verify ownership and keep information up to date.

Installation

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