Audit your AI agent configs before you run them — prompt injection, rogue MCP servers, credential-exfil. Plus dependency vetting.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add zyrax-guard -- npx -y zyrax-guard~/.codex/config.toml
[mcp_servers.zyrax-guard]
command = "npx"
args = ["-y", "zyrax-guard"]
# codex mcp add zyrax-guard -- npx -y zyrax-guard~/.cursor/mcp.json
{
"mcpServers": {
"zyrax-guard": {
"command": "npx",
"args": [
"-y",
"zyrax-guard"
]
}
}
}.vscode/mcp.json
{
"servers": {
"zyrax-guard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"zyrax-guard"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"zyrax-guard": {
"command": "npx",
"args": [
"-y",
"zyrax-guard"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"zyrax-guard": {
"command": "npx",
"args": [
"-y",
"zyrax-guard"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"zyrax-guard": {
"command": "npx",
"args": [
"-y",
"zyrax-guard"
]
}
}
}