Prompt Leak Scanner runs on your own machine — the client starts it, so there is no endpoint to ping. 1 319 installs a week from npm. Last commit 11 Oct 2026.
Catches leaked credentials and PII in outbound LLM prompts
Nothing serious here today
Today is the operative word: we check Prompt Leak Scanner every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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-leak-scanner -- npx -y @guardbee/mcp-prompt-leak-scanner{
"mcpServers": {
"prompt-leak-scanner": {
"args": [
"-y",
"@guardbee/mcp-prompt-leak-scanner"
],
"command": "npx"
}
}
}[mcp_servers.prompt-leak-scanner]
command = "npx"
args = ["-y", "@guardbee/mcp-prompt-leak-scanner"]{
"mcpServers": {
"prompt-leak-scanner": {
"args": [
"-y",
"@guardbee/mcp-prompt-leak-scanner"
],
"command": "npx"
}
}
}{
"mcpServers": {
"prompt-leak-scanner": {
"args": [
"-y",
"@guardbee/mcp-prompt-leak-scanner"
],
"command": "npx"
}
}
}Alternatives to Prompt Leak Scanner
same job, measured the same wayCatches leaked credentials and PII in outbound LLM prompts
Email safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks.
Check text for leaked credentials before an agent writes or commits it. Runs locally.
Secret scanner preventing leaks of corporate keys and credentials.
Mask PII in outbound MCP tool-call arguments, unmask the results. Indian identifiers included.
AI safety middleware — detects self-harm and criminal intent in LLM prompts.
Build, compile, run and export FlagQuantum circuits locally. No credentials or outbound network.
Check products, credentials, claims, and agents against NPC Labs verification records.
Prompt Leak Scanner — questions
Answers built from our own checks of this server.