log-bell/avakill
🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Anthropic, LangChain, and MCP. She doesn't guard. She kills.
Platform-specific configuration:
{
"mcpServers": {
"avakill": {
"command": "npx",
"args": [
"-y",
"avakill"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Loading reviews...