MCPShield

RunTimeAdmin/MCPShield

★ 2 stars Python AI/LLM Updated today

AI agent security platform that discovers, monitors, and assesses the risk of MCP servers across your organization. Automatic scanning on Windows, macOS, and Linux with risk scoring and a centralized multi-tenant dashboard.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcpshield": {
      "command": "uvx",
      "args": [
        "mcpshield"
      ]
    }
  }
}

Or install with pip: pip install mcpshield

README Excerpt

<div align="center"> **Open-source security platform for MCP servers and AI agents** *Discover shadow AI infrastructure. Score every risk. Stop blind spots before attackers find them.* </div> --- Developers are silently connecting AI tools — Claude, Cursor, Windsurf, ChatGPT — to production databases, file systems, shells, and internal APIs via **MCP (Model Context Protocol) servers**. Security teams have zero visibility into this shadow AI infrastructure.

Topics

ai-agentsclaudemcpmodel-context-protocolmonitoringpythonrisk-assessmentsecurity

MCPShield

Quick Install

README Excerpt

Topics

Related AI/LLM Servers