
JWT Tools
MCP serverDecode JWTs without trusting them, flag risky claims, verify signatures, mint test tokens
Runs locally- 3 tools
- Open source
- Security

Decode JWTs without trusting them, flag risky claims, verify signatures, mint test tokens
Runs locallyRules for each agent tool call, then a check of what a database really changed
Runs locally
Self-hosted gateway that lets AI agents use your accounts, with writes held for approval
Not checked yetSends files and secrets from agents to you without putting the link in the chat
Runs locallyLet agents use and save 1Password secrets locally without ever seeing the plaintext
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 locallyScore AI agent runs for quality, PII leaks, prompt injection and cost, on your own machine
Runs locallyInstall and run open-source OSINT tools in a local sandbox, asking before target runs
Runs locallyWrite, test, lint and explain OPA Rego policies from any MCP client
Runs locallyInspect and manage a UniFi network: devices, clients, WiFi, firewall and VPN
Runs locallyRead-only witness for local git projects and sites, naming what would be lost
Runs locallyRead-only search of an OSINT tool and guide registry, with consent classes for each tool
Not checked yetLet a coding agent use temporary credentials without the values entering the chat
Runs locallyEncrypted local secrets vault that lets AI agents use keys without seeing them
Runs locallyJournal, 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 yetSecurity scanner that runs inside your AI editor for code written by AI builders
Not checked yet
Manage Ghost Networks private mesh networks, hubs, VPN and devices from your AI client
Runs locallyLet two companies' AI agents work together on a signed record, with people approving
Not checked yet
Read-only access to an ET Ducky organization's agents, alerts and fleet summary
Not checked yetRead your Golem agent fleet sessions, live activity and signed record from any client
Not checked yetPins MCP tool definitions in a lockfile and flags rug-pulls, poisoning and leaked secrets
Runs locallyRead-only MCP server that lints and budgets CLAUDE.md, AGENTS.md and other steering files
Runs locallyCheck whether your exit IP works for ChatGPT, Claude and Gemini from your AI client
Runs locally
Identity-aware AI tool gateway: every call runs as the requester, under rules, with audit
Not checked yetOffline secret scanning MCP server that returns redacted findings to coding agents
Runs locallyRead-only security scanner for code, infrastructure files and AI agent config
Runs locallyEncrypted local vault where your AI fetches API keys on demand and scans code for leaks
Runs locallyLocal approvals and audit so coding agents use credentials without ever seeing them
Runs locally