Secrets Leak Audit is answering right now. Last checked 4 min ago. Last commit 2 Oct 2026.
Scan text and git diffs for committed credentials using real vendor key formats plus entropy.
Today is the operative word: we check Secrets Leak Audit every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.
claude mcp add secrets-leak-audit-mcp --transport http https://secrets-leak-audit-mcp.mcpize.run/mcp
https://secrets-leak-audit-mcp.mcpize.run/mcp
[mcp_servers.secrets-leak-audit-mcp]
url = "https://secrets-leak-audit-mcp.mcpize.run/mcp"
{
"mcpServers": {
"secrets-leak-audit-mcp": {
"url": "https://secrets-leak-audit-mcp.mcpize.run/mcp"
}
}
}
{
"servers": {
"secrets-leak-audit-mcp": {
"type": "http",
"url": "https://secrets-leak-audit-mcp.mcpize.run/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://secrets-leak-audit-mcp.mcpize.run/mcp | streamable-http | sign-in | 426 ms | 4 min ago |
Check text for leaked credentials before an agent writes or commits it. Runs locally.
Security audit for AI agents — scan code/diffs for leaked secrets, check deps via OSV.
Secret scanner preventing leaks of corporate keys and credentials.
Local secret guardrails: scan code, git changes and MCP configs for API keys; redact text
High-speed regex and entropy-based scanner redacting API keys, JWT tokens, and credentials
Context-aware secret scanner: lets an AI agent scan, verify, and rewrite secrets before committing.
Encrypted secrets and credential management for agents
Credential custody for agents: use secrets blind (ssh/http/smtp/git/db), never in context.
Answers built from our own checks of this server.