Deus Witness
MCP serverHold risky agent actions for passkey approval and keep signed receipts you can verify
Runs locally- Free
- Security
Hold risky agent actions for passkey approval and keep signed receipts you can verify
Runs locallyRun agent-written code under a capability policy and see what it can touch first
Runs locallyEncrypted secrets for agents plus a phone approval step for sensitive actions
Runs locallySecurity verdicts and a runtime guard for agent skills and MCP servers before they run
Runs locallyMask PII and secrets in local memory before text reaches an AI model
Runs locallyLocal anonymiser that swaps client names and amounts for codes before Claude reads files
Runs locallyQuery software inventory, vulnerabilities and end-of-life components
Persistent, local-first memory for agents, stored as plain markdown
Not checked yetAgents 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 yetMenu bar app and MCP server that stop runaway AI agent processes on a Mac
Not checked yetLet 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 locallyLet an agent browse sites where you are already logged in, with encrypted local sessions
Not checked yetOffline scan of local AI agent folders for heartbeat cost, exposed keys and planted memory
Runs locallyRepo triage, bug-fix pull requests and scanner reachability checks for coding agents
Runs locallySee and manage a company's apps, access, devices and spend from an AI assistant
Not checked yet
35 WHOIS, DNS, IP, reputation and threat-intelligence lookups for AI agents
Not checked yetLocal security layer for coding agents: secret redaction, injection checks and MCP proxy
Runs locallyScan 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 yetPer-account allow, ask or block rules for what AI apps may do in your connected services
Not checked yetFree macOS debugging proxy that decrypts HTTPS and lets an assistant drive it over MCP
Runs locallyOrder a dedicated static outbound IPv4 over WireGuard, by API or through an agent
Not checked yetRemote MCP server giving defender agents ledger reads and findings on a coding-agent fleet
Not checked yetSeven-tool proof loop that authorizes agent actions and records tamper-evident evidence
Runs locallyDetect and redact personal data in text, tuned to GDPR, UK GDPR, HIPAA and more
Runs locallySends files and secrets from agents to you without putting the link in the chat
Runs locallyThreat-intelligence verdicts on a URL, domain or IP before a coding agent connects
Not checked yetMove VPN devices between countries and check protection by asking your assistant
Runs locally