Skip to main content
MCP server CX Codex

ClawGuard Shield — Claude Code MCP server: setup and overview

ClawGuard Shield scans text and MCP server configs for prompt injections, jailbreaks, and tool poisoning across 204+ attack patterns in 15 languages.

no license 395 installs updated 2026-03-22

Install into Claude Code · Platform CLI: remote server All methods and platforms ↓
claude mcp add --transport http clawguard https://clawguard--joergmichno.run.tools
Open on GitHub

What ClawGuard Shield does

ClawGuard Shield functions as a hosted agent security scanner accessible at https://clawguard--joergmichno.run.tools. The scan_text tool inspects raw text inputs for jailbreak attempts and adversarial prompts. Every scan reports severity levels, confidence scores, and remediation steps.

Its companion tool, scan_mcp_config, audits settings of other MCP integrations. It flags malicious descriptions, tool poisoning, privilege escalation paths, hidden directives, and exfiltration risks. The scanner is designed with EU AI Act compliance in mind.

Because this server runs remotely over HTTP, your environment must allow outbound traffic to its endpoint.

What it helps with

  • detect prompt injection attacks in user input
  • audit MCP server configs for poisoned tool definitions
  • identify hidden instructions and data exfiltration vectors
  • verify compliance with EU AI Act security requirements

Example prompts for the agent

  • Scan this user input for prompt injection with scan_text
  • Check our MCP config JSON for tool poisoning using scan_mcp_config
  • Analyze tool descriptions for hidden commands or exfiltration vectors

How to install ClawGuard Shield

Platform CLI: remote server

claude mcp add --transport http clawguard https://clawguard--joergmichno.run.tools

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about ClawGuard Shield

How to install ClawGuard Shield in Claude Code?

Run claude mcp add --transport http clawguard https://clawguard--joergmichno.run.tools. Claude Code connects to the remote HTTP endpoint without local package installs.

What does ClawGuard Shield do?

It inspects prompts and MCP server configurations in real time. The scanner flags jailbreaks, tool poisoning, and prompt injections across 15 languages.

What vulnerabilities does scan_mcp_config detect?

The tool detects permission escalation vectors, hidden instructions, prompt injections inside tool schemas, and data exfiltration points.

Similar MCP servers

All MCP servers for Security →

Project sponsors

Companies that keep this analytics open