cheap-eyes runs on your own machine — the client starts it, so there is no endpoint to ping. 184 installs a week from npm. Last commit 15 Oct 2026.
Hands bulk reading to cheap OpenRouter models, masks secrets, checks each answer against the source
What the code does
We read the source, 23 h ago · rules ccca72095570
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.
return JSON.parse(await fs.readFile(path.join(sourcesDir(resultsDir, id), 'index.json'), 'utf8'));
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
Connect this server
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 cheap-eyes -- npx -y cheap-eyes{
"mcpServers": {
"cheap-eyes": {
"args": [
"-y",
"cheap-eyes"
],
"command": "npx"
}
}
}[mcp_servers.cheap-eyes]
command = "npx"
args = ["-y", "cheap-eyes"]{
"mcpServers": {
"cheap-eyes": {
"args": [
"-y",
"cheap-eyes"
],
"command": "npx"
}
}
}{
"mcpServers": {
"cheap-eyes": {
"args": [
"-y",
"cheap-eyes"
],
"command": "npx"
}
}
}This one needs environment variables set before it will start:
CHEAP_EYES_OPENROUTER_KEY (OpenRouter API key (give it its own daily limit on openrouter.ai)), CHEAP_EYES_CONFIG (Path of the JSON config file (read roots, model aliases); optional).
The author declared them in the registry entry; get the values from the project itself.
Alternatives to cheap-eyes
same job, measured the same waySecurity scanning for AI coding tools. Detects secrets, threat models, and runs pre-commit checks.
Detect hardcoded secrets in source and config. Reports masked previews, never the values.
Use this MCP server to OSV open source vulnerability data and package security checks. Tools...
Large files and secrets between people and agents, never through the chat or the model.
Security tools for your AI: scan, pentest, check headers, guard code and scan repos for secrets.
Injects secrets into shell commands at exec time; plaintext never reaches the LLM context
Reads your SECURITY.md against the EU Cyber Resilience Act reporting clock that started on 11 Septem
Read-only Kubernetes MCP server: inspect resources, logs, events, and metrics. Secrets are masked.
cheap-eyes — questions
Answers built from our own checks of this server.