prompt-protection runs on your own machine — the client starts it, so there is no endpoint to ping. 1 267 installs a week from npm. Last commit 30 Oct 2026.
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
What the code does
We read the source, 3 d ago · rules 995398eba69f
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.
subprocess.run(["node", str(HERE / "normalize.mjs"), "--strings", str(inp), str(outp)], check=True)
'/wH//Pv9/AEABf8IAQAAAQEA/wMCAAD//woD/f8BAPz3Af8AAgD5/wAABAECAgD//wIAAAEAAAD+AAAA+gPp/wADAAD7AP/3AAD//P38/gD//wEE/wAA/vwUAQMD/wD0AAD+CAAABv4C+/8AAAIEAP//A/3/AvwAAAQBAQH8AAAB9AIEAAAAAADkAvP/AAQJAv8AAQH+/v//AQECAf3/+v8A/AABAAYDAAABAQEB/wH6/v/+/wH+AAMA/QH+/v8AAP8C+gEAAAMAAfQA/AAAA…
pattern: /(read|open|output|return|show|cat|print)\s+.{0,20}(\/etc\/passwd|\/etc\/shadow|\/etc\/hosts|\.env|secrets?\.json|credentials?\.json|config\.json|id_rsa)/,
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 prompt-protection -- npx -y prompt-protection{
"mcpServers": {
"prompt-protection": {
"command": "npx",
"args": [
"-y",
"prompt-protection"
]
}
}
}[mcp_servers.prompt-protection]
command = "npx"
args = ["-y", "prompt-protection"]{
"mcpServers": {
"prompt-protection": {
"command": "npx",
"args": [
"-y",
"prompt-protection"
]
}
}
}{
"servers": {
"prompt-protection": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"prompt-protection"
]
}
}
}Alternatives to prompt-protection
same job, measured the same wayScan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
Scans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex
Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools
Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
Deterministic prompt-injection detection & sanitization for AI agents via x402 on Base.
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
prompt-protection — questions
Answers built from our own checks of this server.