
MCP security audit
SkillAudits MCP server configs for leaked secrets, shell injection and unpinned package runners
- Open source
- 41.3K GitHub stars
- Security

Audits MCP server configs for leaked secrets, shell injection and unpinned package runners

Audits and hardens GKE workload security: network policies, pod standards, gVisor

Guides Java code to store, read, rotate and back up secrets in Azure Key Vault

Lets an agent store, read, update, list and delete Azure Key Vault secrets in Rust

Guides an agent through storing, reading and rotating Azure Key Vault secrets
Encrypted vault for .env files with scoped, audited MCP access for coding agents
A safer MCP for Dokploy: agents deploy and fix apps without seeing keys or secrets
Not checked yetEncrypted secrets for agents plus a phone approval step for sensitive actions
Runs locallyGives coding agents your API keys without letting the model ever read them
Runs locallyMask PII and secrets in local memory before text reaches an AI model
Runs locally
Rank security scanner findings by exposure, criticality and exploitability
Runs locallyKeep API keys in your OS keychain and give coding agents only what policy allows
Runs locallyAgents use your API keys, SSH keys and wallets via a local broker and never hold them
Runs locallyLint CLAUDE.md, AGENTS.md and .mcp.json against your actual codebase
Runs locallyLint a SKILL.md for missing triggers, leaked secrets and injection markers before install
Not checked yetLocal deterministic security scan of your workspace with fix guidance for your AI agent
Runs locallyScan AI coding session logs and assistant configs for leaked secrets and risky hooks
Runs locallyLet agents run commands with your secrets without ever seeing the values
Runs locallyKeeps API key values out of AI chats and deploys them to Cloudflare, Vercel or GitHub
Runs locally
Check AI-written code for leaked keys and invented packages on your own machine
Not checked yetPrompt-injection scanner and tool-call gate for AI agents, run locally over stdio
Runs locallyRequest or send secrets for an agent without them ever appearing in the chat
Runs locallyLet AI agents run commands with your secrets while the values stay hidden and redacted
Runs locallySafety checks for AI agents: page reading, prompt injection, secrets and PII scans
Not checked yetLocal security layer for coding agents: secret redaction, injection checks and MCP proxy
Runs locallyMac key vault where agents get scoped, expiring tokens and never the API keys
Runs locallyLocal security scanner that checks AI-written code and drives a scan, fix, rescan loop
Runs locallyFind leaked API keys and passwords in pasted text, flag live ones, and redact
Not checked yetScan which credentials an AI coding agent running as you could read, offline
Runs locallyScan MCP configs for leaked secrets and poisoned tools, and review AI-written code
Not checked yetThe most popular MCP servers and agent skills for secrets on AI-Powered right now are MCP security audit, Gke workload security, Azure security keyvault secrets java, Azure keyvault secrets rust and Azure keyvault secrets ts. Rankings combine upvotes, recent activity and, for open-source projects, GitHub stars.
Yes. Of the 62 MCP servers and agent skills for secrets listed, 31 are free or open source and 28 have a free plan. Use the Pricing filter to see only those.
AI-Powered lists 62 MCP servers and agent skills for secrets. New listings are added daily from the official MCP Registry, GitHub and maker submissions.