The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Secrets Audit MCP listing page.
MCP server that detects leaked credentials in source code. Zero dependencies. Single file.
Detects API keys, OAuth tokens, private keys, webhooks, and crypto wallet secrets across 30+ providers (AWS, GCP, GitHub, Stripe, OpenAI, Anthropic, Slack, Discord, Telegram, Twilio, SendGrid, Heroku, DigitalOcean, npm, HuggingFace, Replicate, Cloudflare, and more).
Companion to skill-audit-mcp (behavioral patterns) — together they cover secrets + behaviors in one MCP toolchain.
Most secret scanners are giant Go binaries (trufflehog, gitleaks). This is
a 500-line Python file that runs as an MCP stdio server, so any LLM agent
(Claude Desktop, Cursor, Windsurf, Cline) can ask it scan_directory and
get a structured report in their tool-call response.
Use cases:
| Tool | Use case |
|---|---|
scan | Scan inline text/content |
scan_file | Scan a single file |
scan_directory | Scan a directory recursively (skips .git, node_modules, __pycache__, etc.) |
All return a risk score (0-100), severity bucket (CRITICAL/HIGH/MEDIUM/LOW/SAFE),
and per-finding details with line numbers and redacted matches.
Providers (32 rules total):
apikey="..." heuristic, generic secret assignmentsEach match is redacted (AKIA***MPLE) before being returned, so the report
itself doesn't leak the secret to the next LLM hop.
A first-class GitHub Action will ship as eltociear/secrets-audit-action@v1.
skill-audit-mcp covers behavioral malware patterns (download-and-execute, prompt injection, credential exfiltration). Run both for full coverage:
| Layer | Tool | Detects |
|---|---|---|
| Static behaviors | skill-audit-mcp | curl-pipe-sh, exfiltration, prompt injection (68 patterns) |
| Static secrets | secrets-audit-mcp | leaked keys/tokens/PEMs (32 rules) |
Polar.sh — Security Pulse Monthly ships a monthly briefing on new MCP server vulnerabilities, secrets-audit-mcp rule updates, and mitigation playbooks. $5/mo.
Polar.sh — Pro Audit Stack adds 50 paid scan credits + Discord + custom rule submission. $20/mo.
MIT. See LICENSE.
This MCP server is free. For server-side / batch / no-install use, the same scanner is a pay-per-call x402 HTTP API: POST https://eltociear-secrets-audit.hf.space/audit ($0.01 USDC on Base) and /audit/url ($0.03). In the official MCP Registry as io.github.eltociear/secrets-audit-mcp.
Maintained by the same author — paid services on Polar (Stripe checkout):
Full catalog: polar.sh/eltociear
Same operator, same x402 rails: clean-read turns any URL into clean Markdown for AI agents — fetches the page, strips nav/ads/boilerplate (trafilatura), returns the main content with title and word count. POST https://eltociear-skill-audit.hf.space/read — $0.005 USDC on Base, no signup.