Claude MarketplacesSubmit
eltociear avatar

Secrets Audit Mcp

eltociear/secrets-audit-mcp

This is a lightweight secret scanner that runs as an MCP stdio server, exposing three tools: scan inline text, scan a single file, or scan an entire directory recursively. It detects 32+ credential patterns including AWS keys, GitHub tokens, Stripe secrets, OpenAI and Anthropic API keys, private PEM blocks, and Ethereum wallet keys. Every match gets redacted before returning to the LLM, so your agent gets a risk score and line numbers without leaking the actual secret downstream. It's a 500-line Python file with zero dependencies, purpose-built for agent-driven code review, pre-commit checks, or auditing repos before you clone them into your shell. Ships alongside a sister project for behavioral malware patterns if you want full static coverage.

tools
3
transport
STDIO
last updated
Jun 7, 2026
View on GitHub

Tools

3 tools

Public tool metadata for what this MCP can expose to an agent.

scanScan inline text/content

Scan inline text/content

No parameter schema in public metadata yet.

scan_fileScan a single file

Scan a single file

No parameter schema in public metadata yet.

scan_directoryScan a directory recursively (skips .git, node_modules, __pycache__, etc.)

Scan a directory recursively (skips .git, node_modules, __pycache__, etc.)

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

secrets-audit-mcp

smithery badge MCP Registry

MCP server that detects leaked credentials in source code. Zero dependencies. Single file.

License: MIT Python 3.6+ MCP Sister: skill-audit-mcp

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.

View the full README on GitHub

Details

Repository
github.com/eltociear/secrets-audit-mcp
Categories
AI & LLM Tools, Cloud & Infrastructure, Developer Tools, Finance & Commerce
Package
ghcr.io/eltociear/secrets-audit-mcp:1.0.1
Transport
STDIO
Registry
MCP registry, active

More from eltociear

Related AI & LLM Tools MCP servers

View all
1freeguy-ai avatarCloseread Verifyfreeguy-ai/closeread-verifyA verified dependency-audit verdict any AI agent can call over MCP, not a raw scan.0stars
2freminder avatarESG MCP Serversfreminder/esg-mcp-servers31 MCP tools for ESG data extraction, PDF processing, vector search, and EU regulation analysis.0stars
3getcyphrex avatarCyphrexgetcyphrex/platformChecks AI agent actions before they run. Signed, RFC 3161 timestamped evidence for audits.0stars
4goatgaucho avatarTrustLayergoatgaucho/trust-layerAgent reputation scoring: trust scores, Sybil detection, cross-chain identity for 133K+ agents0stars
5goodmeta avatarIntelligence Mcpgoodmeta/intelligence-mcpAgent payments ecosystem intelligence. Scans GitHub/HN/npm across AP2, ACP, x402, MPP, UCP.0stars
6gsepcore avatarGsep Mcpgsepcore/gsep-mcpAI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.0stars