Umbryn Mcp

Overview

Umbryn Mcp is a Model Context Protocol server that redacts personally identifiable information and protected health information from text before it reaches an LLM. It operates fail-closed with no data egress, keeping sensitive content secure within your environment. By implementing MCP, it lets AI assistants call redaction as a native tool rather than requiring manual copy-paste between applications.

The server runs entirely locally as the Python package umbryn-mcp, invoked via uvx umbryn-mcp. It communicates over stdio and requires no authentication or external credentials to operate. Version v0.2.1 is available under the MIT license with source code at Rinava/umbryn-mcp on GitHub.

Umbryn Mcp is listed in the AI & Agents category on mcp.site and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this project, claim the listing to verify ownership and keep information up to date.

Installation

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