Zentric Protocol Mcp

Overview

Zentric Protocol Mcp is a Model Context Protocol server that detects prompt injection attacks and personally identifiable information in LLM applications and agent pipelines. Its deterministic detection runs in under 25 milliseconds, allowing any MCP-compatible AI assistant to call its tools directly during conversations or agent runs.

The server runs locally via the npm package zentric-protocol-mcp, which communicates over stdio without requiring any credentials or setup. The current release is v0.1.3, with source code available at ZentricProtocol/zentricprotocol on GitHub under an open development model.

Zentric Protocol Mcp is categorized as AI & Agents on mcp.site and integrates with all MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this server, claim your listing to verify ownership and ensure the information stays accurate.

Installation

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