
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
A safer MCP for Dokploy: agents deploy and fix apps without seeing keys or secrets
Not checked yetGives coding agents your API keys without letting the model ever read them
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 locallyLint CLAUDE.md, AGENTS.md and .mcp.json against your actual codebase
Runs locallyPrompt-injection scanner and tool-call gate for AI agents, run locally over stdio
Runs locallyLet AI agents run commands with your secrets while the values stay hidden and redacted
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 locallyGive an AI assistant its own Bitwarden vault for logins, 2FA codes and passkeys
Runs locallyOffline security scans for AI-written code: seven open-source scanners, one report
Runs locallyCollect API keys in a browser page and write them to .env without the model seeing them
Runs locallySecrets manager MCP server that runs commands with API keys the model never sees
Runs locallyLet agents use and save 1Password secrets locally without ever seeing the plaintext
Runs locallyLocal MCP server that redacts personal data and secrets in text before it reaches a model
Runs locallySecret broker that injects credentials at the point of use, never into the model
Runs locallyLocal checks for sudo, systemd, sshd, ufw and secret leaks before an agent runs commands
Not checked yetPins MCP tool definitions in a lockfile and flags rug-pulls, poisoning and leaked secrets
Runs locallyLocal MCP tools that redact secrets in files, scan commits and verify webhooks for agents
Runs locallymacOS Keychain secret broker where an agent can use your API keys but never read them
Runs locally