MCP server guardrail that detects prompt injection attempts hidden in forensic artifacts before they reach an AI-based IR agent context. Built for SANS FIND EVIL! hackathon.
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Claude Desktop
Claude Code
Cursor
Add to claude_desktop_config.json:
{
"mcpServers": {
"sentinel-mcp-guardra": {
"command": "uvx",
"args": [
"sentinel-mcp-guardrail"
]
}
}
}📋 Copy
Run in terminal:
claude mcp add sentinel-mcp-guardra uvx sentinel-mcp-guardrail📋 Copy
Add to .cursor/mcp.json:
{
"mcpServers": {
"sentinel-mcp-guardra": {
"command": "uvx",
"args": [
"sentinel-mcp-guardrail"
]
}
}
}📋 Copy
Or install with pip: pip install sentinel-mcp-guardrail