Zyrax Guard runs on your own machine — the client starts it, so there is no endpoint to ping. 60 installs a week from npm. Last commit 12 Aug 2026.
Audit AI agent configs for prompt injection & rogue MCP servers; vet packages
We read the source, 20 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
blobPath := filepath.Join(dir, asset)
`(\.env\b|id_rsa\b|id_ed25519\b|` +
`(\.env\b|id_rsa\b|id_ed25519\b|` +
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add zyrax-guard -- npx -y zyrax-guard
{
"mcpServers": {
"zyrax-guard": {
"args": [
"-y",
"zyrax-guard"
],
"command": "npx"
}
}
}
[mcp_servers.zyrax-guard]
command = "npx"
args = ["-y", "zyrax-guard"]
{
"mcpServers": {
"zyrax-guard": {
"args": [
"-y",
"zyrax-guard"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"zyrax-guard": {
"args": [
"-y",
"zyrax-guard"
],
"command": "npx"
}
}
}
Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.
Defense-in-depth for MCP stdio servers: shell-injection guard, AST audit CLI, RCE blocking.
Scan an MCP server or agent config for injection, exfiltration, and risky capabilities.
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
Scan for prompt injection, secrets, PII, and vet MCP servers before installation
Audit MCP configs and skill files for over-broad scope and injection risk. 6 of 8 free.
Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs
lu.ma events MCP server with draft+confirm safety, audit logging, and prompt-injection scrubbing.…
Answers built from our own checks of this server.