Deterministic AST circuit breaker that blocks risky agent code before it runs
Not checked yet- Remote
- Open source
- Security
Deterministic AST circuit breaker that blocks risky agent code before it runs
Not checked yetOpen internet-censorship data for agents, plus gated payment and mail tools
Not checked yet
Check whether a server software version is exploited, end of life or has a fix
Not checked yetSigned checks of x402 sellers on Base and remote MCP servers before your agent pays
Not checked yetValidate v3 onion addresses and fetch a known test specimen; research logging disclosed
Not checked yetWrite, test, lint and explain OPA Rego policies from any MCP client
Runs locallyCountersigned proof-of-delivery receipts for work sold between AI agents
Not checked yetHosted permission checks, human approvals and audit logs for AI agent tool calls
Not checked yetRead-only domain security checks for dApp frontends: locks, DNSSEC, CAA, SRI and SEAL
Not checked yet
Static safety scan of MCP configs that returns SAFE, REVIEW, BLOCK or UNKNOWN verdicts
Runs locallySourced privacy answers: app privacy checks, tool picks, swaps and breach lookups
Not checked yetInspect and manage a UniFi network: devices, clients, WiFi, firewall and VPN
Runs locally
Self-hosted OWASP ZAP operator that lets AI agents run guided security scans and reports
Not checked yetRun a free passive security scan on an AI-built web app from Claude, ChatGPT or Cursor
Not checked yetFail-closed privacy layer that pseudonymises enterprise API data for LLM agents
Not checked yetFind hidden Unicode, homoglyphs and lookalike names in text before an agent acts on it
Not checked yetRead-only witness for local git projects and sites, naming what would be lost
Runs locallyShare documents as tracked, identity-gated links that an AI agent can create but not read
Not checked yetAudits a live URL with 85 SEO, AI-search, security and speed checks
Not checked yetRead-only search of an OSINT tool and guide registry, with consent classes for each tool
Not checked yetSecret broker that injects credentials at the point of use, never into the model
Runs locallyLet a coding agent use temporary credentials without the values entering the chat
Runs locallyNumbered, signed blank forms that let two agents co-sign deal terms and prove them later
Not checked yetOpen forum and end-to-end encrypted direct messages for AI agents, keys held client-side
Runs locallySigned pre-flight verdicts on MCP servers: bad identity, CVEs, dependencies, drift
Not checked yetScan MCP tool definitions for poisoning, check a server's change history, count token cost
Not checked yetJournal, approve or block, and sandbox every MCP tool call your AI agent makes
Runs locallySearch a Japanese security camera and IoT shop's pages from an AI app, no account
Not checked yetLocal static audit of AI model files with hash-bound evidence for deployment reviews
Not checked yetManage SimpleLogin aliases, mailboxes, domains and settings from an MCP client
Runs locallySee every kind of AI for security: tools, agents, MCP servers and skills.Ranked: the best AI for security.