Portunus
MCP serverSecret broker that injects credentials at the point of use, never into the model
Runs locally- Open source
- Security
Secret broker that injects credentials at the point of use, never into the model
Runs locallyRead-only TLS certificate and domain registration expiry checks, no sign-in needed
Not checked yetEncrypted local secrets vault that lets AI agents use keys without seeing them
Runs locallyScan a GitHub repository for vulnerabilities from a coding agent, with proof per finding
Not checked yetCheck what a repository would run on your machine before you clone or open it
Runs locallyPasskey login API for existing sign-in systems, with MCP project and key setup
Not checked yetCheck x402 payment requests and Québec contractors before your agent pays
Not checked yetOpen forum and end-to-end encrypted direct messages for AI agents, keys held client-side
Runs locallyRemote MCP package of 12 pre- and post-execution security checks for autonomous agents
Not checked yetRemote MCP set of 15 smart-contract, Solana and HTTP 402 security checks for DeFi agents
Not checked yetGrade a domain's email security and get exact fixes for SPF, DKIM, DMARC, TLS and DNSSEC
Not checked yetRead-only checks for DIDs, credentials, MCP servers, A2A agent cards and delegation
Not checked yetScreen 1 to 100 names against 10 official sanctions lists, with scored candidate matches
Not checked yetJournal, approve or block, and sandbox every MCP tool call your AI agent makes
Runs locallySwiss encrypted cloud drive for AI agents: search, read, save and share files
Not checked yetCheck x402 sellers and get signed receipts before an AI agent pays
Runs locallyLocal static audit of AI model files with hash-bound evidence for deployment reviews
Not checked yetSecurity scanner that runs inside your AI editor for code written by AI builders
Not checked yetManage SimpleLogin aliases, mailboxes, domains and settings from an MCP client
Runs locallyCheck what a site's cookie banner blocks, from ChatGPT, Claude, Claude Code or Cursor
Not checked yetSpending control for AI agents: owner-approved budgets, a decision before each payment
Not checked yetSigned, hash-chained receipts of an AI agent's decisions with public proof links
Not checked yetQuery login risk scores, blocked logins and Tor, VPN and bot traffic by chat
Not checked yetBrowse and fetch React and Next.js interaction effects from the Hyperiux Vault registry
Runs locallyOpen-source MCP proxy that enforces policies, budgets and approvals on agent tool calls
Not checked yetLicence checks, signed receipts and pre-call guards for AI agents
Not checked yetDeterministic URL risk checks with dated evidence, batches of ten and capped prepaid costs
Not checked yetVerify blockchain timestamp proofs offline and anchor file hashes through ProofLedger
Runs locallyDetect AI-generated speech, verify speakers by voice and classify who answered a call
Not checked yetRisk check for Robinhood Chain and Solana tokens before an agent buys, plus trade tools
Not checked yet