scan_for_prompt_injection

MCP tool from EU AI ACT MCP by SonnyLabs

Purpose: Detect prompt injection attacks in real-time

How to use it

scan_for_prompt_injection is exposed by the EU AI ACT MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the scan_for_prompt_injection tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install EU AI ACT MCP

$pip install -r requirements.txt

FULL EU AI ACT MCP LISTING

Other tools in EU AI ACT MCP (10)

check_prohibited_practices

Purpose: Check if your AI violates Article 5 prohibited practices

check_sensitive_file_access

Purpose: Monitor AI agent file access for security

classify_ai_system_risk

Purpose: Determine if your AI system is Prohibited, High-Risk, Limited-Risk, or Minimal-Risk

determine_eu_ai_act_role

Purpose: Identify your role under EU AI Act (Provider, Deployer, etc.)