Szesnasty/ai-protector
Self-hosted LLM firewall and agent guardrails that block prompt injection, redact PII, enforce RBAC, and secure tool calls.
Platform-specific configuration:
{
"mcpServers": {
"ai-protector": {
"command": "npx",
"args": [
"-y",
"ai-protector"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Loading reviews...