Mund — MCP Security Scanner

Overview

Mund — MCP Security Scanner is a Model Context Protocol (MCP) server: Scan for prompt injection, secrets, PII, and vet MCP servers before installation. In practice that means any MCP-compatible AI assistant can call Mund — MCP Security Scanner's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the npm package @weave_protocol/mund speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.1.12, published under the Apache-2.0 license, with source at Tyox-all/Weave_Protocol on GitHub.

Mund — MCP Security Scanner is listed under Security on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Mund — MCP Security Scanner for Tyox-all, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "mund_mcp_security_scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@weave_protocol/mund"
      ]
    }
  }
}