Review what your AI touched, approve risky actions and undo supported changes
- 1 tool
- Remote
- Free
- 1 GitHub star
- Security
Review what your AI touched, approve risky actions and undo supported changes
Free pre-execution checks on who can change a DeFi contract, before an agent calls it
Regulation-citing tools for trucking, OSHA, 811 dig times, eCFR and Coast Guard records
Hold risky agent actions for passkey approval and keep signed receipts you can verify
Runs locallyScan PDF, Office, RTF and HTML files for hidden text before an agent reads them
Encrypted secrets for agents plus a phone approval step for sensitive actions
Runs locally
Keyless CVE, KEV, EPSS and advisory lookups with per-CVE internet exposure counts
Agents use your API keys, SSH keys and wallets via a local broker and never hold them
Runs locallySealed microVM sandboxes for agents to run untrusted code, locally or in the cloud
Not checked yetChecked inbound email, held outbound sends and approved Meet calls for AI agents
Not checked yetGrade your installed MCP servers A to D from public signals, with safer alternatives
Runs locallyGuard that checks MCP tool calls against a passkey-signed permission and logs receipts
Runs locallyLet agents run commands with your secrets without ever seeing the values
Runs locally
Read-only product, pricing and quote answers about BlueNOC firewall monitoring
Not checked yetSafety grades for MCP servers and APIs, with wrap and lockfile modes to catch tool changes
Runs locallyAsk business questions across connected enterprise systems with governed definitions
Not checked yetScan npm packages and MCP servers before install, with SAFE, REVIEW or BLOCK verdicts
Not checked yetLet an agent browse sites where you are already logged in, with encrypted local sessions
Not checked yetLook up IP risk signals and review risky website visits with FindIP Shield
Runs locallyKeyless DeFi risk grades, quantum readiness and hack incidents for AI agents
Runs locally
Manage managed Keycloak clusters, realms, SSO and users from an MCP client
Not checked yetGrade an AI-built app from A to F for leaked keys and open data, with fix prompts
Runs locallySearch, read and write a folder of Markdown notes with hybrid keyword and meaning search
Not checked yetRead-only-by-default tools for each Keycloak admin operation on a single realm
Runs locallyVerify PDF signatures, detect tampering and get a trust verdict for incoming files
Runs locallyLet your coding agent publish a card, find matching agents and negotiate behind a firewall
Not checked yetOffline MCP scanner that inventories quantum-vulnerable cryptography in a code repository
Runs locally
Look up an IP address's abuse score and report attackers to a shared database
Not checked yetRead-only graph linking CVEs, exploited lists, ATT&CK and detections, with sources
Not checked yetSee every kind of AI for security: tools, agents, MCP servers and skills.Ranked: the best AI for security.