TrustGrade — The Trust Layer for AI Agents

🔌 MCP-Native · Model Context Protocol

TrustGrade

The Trust Layer for AI Agents

Before your agent acts, it checks TrustGrade.

A+ Uniswap A+ USDC B+ Curve F USTC

# Agent checks trust before executing curl https://api.trustgrade.ai/v1/score/stablecoin/USDC { "score": 100, "grade": "A+", "confidence": 0.98 } # Agent proceeds ✅ curl https://api.trustgrade.ai/v1/score/stablecoin/USTC { "score": 12, "grade": "F", "confidence": 0.95 } # Agent aborts 🚫

45+

Entities Scored

Entity Types

MCP Tools

<50ms

API Latency

Public API — No Auth Required

GET /v1/health — health check

GET /v1/entity-types — supported types

GET /v1/stats — protocol stats

GET /v1/score/:type/:id — cached score lookup

POST /v1/score — compute new score (auth)

API Docs → MCP Setup → Registry →