This release includes 1 security fix for security teams reviewing exposed deployments.
Summary
AI summaryAdded three npm integration packages for agent frameworks and hardened trust score calculations.
Full changelog
🔌 Agent Integration Packages
Three npm packages to plug Maiat trust scoring into any agent framework:
| Package | Install |
|---------|---------|
| MCP Server (Claude/OpenClaw) | npm install @jhinresh/mcp-server |
| ElizaOS Plugin (ai16z) | npm install @jhinresh/elizaos-plugin |
| AgentKit Plugin (Coinbase) | npm install @jhinresh/agentkit-plugin |
MCP Server
Add to Claude Desktop / OpenClaw config — tools: maiat_check_trust, maiat_check_token, maiat_batch_check
ElizaOS Plugin
Auto-gates swaps for low-trust addresses. Drop-in plugin for any ElizaOS agent.
AgentKit Plugin
Wrap any Coinbase AgentKit action with trust gating before execution.
Other Changes in this release
- Pencil frontend redesign (homepage, explore, score pages)
- Trust score hardening — seed data protection, weight alignment, isStale detection
/explorepage with live API data/swappage restored- Supabase review API + Prisma migration
- Open API v1 (
/api/v1/score/{address},/api/v1/review,/api/v1/swap) - Security audit fixes (AccessControl, Pausable, batch limits)
- 60 Foundry tests passing
Links
- 🌐 Live: https://maiat-protocol.vercel.app
- 📦 npm: https://www.npmjs.com/org/jhinresh
- 🔗 Contracts (Base Sepolia):
0xF662902ca227BabA3a4d11A1Bc58073e0B0d1139
Security Fixes
- Security audit fixes addressing AccessControl, Pausable, and batch limits issues
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About JhiNResH/maiat-protocol
Trust infrastructure for the agent economy. 4 tools: agent trust scores (18K+ agents indexed)
Related context
Related tools
Beta — feedback welcome: [email protected]