Zn Gate runs on your own machine — the client starts it, so there is no endpoint to ping. 506 installs a week from npm. Last commit 15 Oct 2026.
Local security layer for coding agents: secret redaction, prompt-injection checks and MCP proxy.
We read the source, 4 min ago · rules ccca72095570
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
fs.writeFileSync(opened.fd, text);
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
/\b(?:send|upload|post|exfiltrate|forward|transmit|leak|e-?mail|copy|share|paste)\b[^\n]{0,120}?(?:\.env\b|~\/\.ssh|id_rsa|id_ed25519|\.aws\/credentials|\.npmrc|\.netrc|\.git-credentials|api[ _-]?keys?|access[ _-]?tokens?|secrets?|credentials?|passwords?|private[ _-]?keys?|envi…
… _-]?keys?|environment variables)\b[^\n]{0,120}?(?:https?:\/\/|webhook|pastebin|discord(?:app)?\.com|gist\.github|ngrok|requestbin|attacker)/i,
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.
/\b(?:curl|wget|http|iwr|invoke-webrequest|invoke-restmethod)\b[^\n|]{0,200}?(?:-d|--data(?:-binary|-raw|-urlencode)?|-F|--form|-T|--upload-file|--post-file|-InFile|-Body)[\s=]{1,3}["']?@?[^\s"']{0,40}?(?:\.env\b|\.ssh\/|id_rsa|id_ed25519|\.aws\/credentials|\.npmrc|\.netrc|\.git-credentials)/i,
const res = spawnSync(cmd, args, {
for (const x of exts) out.push(path.join(dir, name + x));
pattern: /(?:^|[\s"'`(\[])(?:~|\/home\/[^\s/]+|\/root)?\/?\.(?:ssh\/(?:id_rsa|id_ed25519|authorized_keys)|aws\/credentials|env(?:\.[a-z0-9]+)?)(?![A-Za-z0-9_])|\/etc\/(?:shadow|passwd)(?![A-Za-z0-9_])/i,
… _-]?keys?|environment variables)\b[^\n]{0,120}?(?:https?:\/\/|webhook|pastebin|discord(?:app)?\.com|gist\.github|ngrok|requestbin|attacker)/i,
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
- name: Delete caches of closed pull requests
env:
GH_TOKEN: ${{ github.token }}
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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 zn-gate -- npx -y zn-gate
{
"mcpServers": {
"zn-gate": {
"args": [
"-y",
"zn-gate"
],
"command": "npx"
}
}
}
[mcp_servers.zn-gate]
command = "npx"
args = ["-y", "zn-gate"]
{
"mcpServers": {
"zn-gate": {
"args": [
"-y",
"zn-gate"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"zn-gate": {
"args": [
"-y",
"zn-gate"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
ZN_LOCAL_ONLY (Set to true to force local-only mode, even if ZN_CLOUD=1.), ZN_CLOUD (Set to 1 to let prompt analysis also query the optional cloud classifier. Off by default.), ZN_API_KEY (API key for the optional cloud check. Has no effect without ZN_CLOUD=1.).
The author declared them in the registry entry; get the values from the project itself.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Multi-agent LLM security layer detecting prompt injection and jailbreaks.
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
Real-time semantic security for AI coding agents and MCP tools
Security for AI agents: MCP audits, secret redaction, skill vetting, network scans, agent checkout.
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
Scan for prompt injection, secrets, PII, and vet MCP servers before installation
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
Answers built from our own checks of this server.