# MolTrust Trust Registry

> Production trust infrastructure for autonomous AI agents. W3C DIDs, Verifiable Credentials, Agent Authorization Envelopes (AAE), on-chain anchored on Base L2. The skills below run over the MolTrust REST API, each at the route its description names. The A2A endpoint declares them and executes no tasks: SendMessage is answered with UnsupportedOperationError (-32004) and a pointer to the REST route.

- **Domain**: `api.moltrust.ch`
- **Provider**: CryptoKRI GmbH (https://moltrust.ch)
- **A2A protocol version**: 1.0
- **Kind**: paid_api
- **Live-responds (last probe)**: True
- **Signed card**: True
- **Streaming**: False
- **Quality score**: 100%
- **Payment protocol**: x402 · network `eip155:8453`

## Skills
- **Agent Trust Score** — Returns W3C DID-based trust score (0-100) with behavioral history breakdown, sybil penalty, anomaly flags, on-chain proof. Cross-vertical aggregation across Spo
- **DID Resolution** — Resolves W3C Decentralized Identifiers (did:moltrust) to DID Documents with verification methods and service endpoints. DIF Universal Resolver compatible (drive
- **Verifiable Credential Verification** — Verifies W3C Verifiable Credentials including Agent Authorization Envelopes (AAE) with delegation chain validation. Supports issuance via /credentials/issue and
- **Wallet Binding Verification** — Checks whether an agent DID has a wallet bound and is ready for x402 payment: bound wallet, chain, trust score, payment readiness and when the binding was made.
- **Wallet Track Record Credential** — Issues a TrackRecordCredential over a wallet bound to the DID, stating what that wallet has done on Base: transactions sent, age in days, transfer count, USDC v
- **Sybil & Anomaly Detection** — Two-layer sybil detection: (1) embedded in trust-score response (flags array + sybil_penalty in breakdown), (2) dedicated paid endpoint via MoltGuard with on-ch
- **EU AI Act risk classification** — Classify an AI system under Regulation (EU) 2024/1689: risk tier (prohibited/high/limited/minimal), obligations checklist, gap analysis, with EUR-Lex article pi
- **EU declaration of conformity (Annex V)** — Issue an Annex V EU declaration of conformity as a signed W3C Verifiable Credential (MolTrustConformityDeclaration). Served over REST, not as an A2A task: POST 
- **Compliance report** — HTML/JSON report: identity, latest risk assessment, obligations, gaps, declarations on record, audit summary. Served over REST, not as an A2A task: GET /complia
- **Article 73 serious-incident recording** — Record an Article 73 serious incident and compute its staggered reporting deadline (2/10/15 days) with deadline status. Served over REST, not as an A2A task: PO
- **UCAN delegation minting** — Mint a UCAN 0.10.0 delegation token with scoped capabilities, attenuation and a proof chain. Served over REST, not as an A2A task: POST /delegation/create (X-AP
- **UCAN delegation verification** — Verify a UCAN token and its proof chain: signature, time bounds, iss/aud alignment, attenuation monotonicity, revocation. Served over REST, not as an A2A task: 
- **Batch reputation** — Reputation scores and ratings for up to 500 agent DIDs in a single call. Served over REST, not as an A2A task: POST /reputation/batch-sync (X-API-Key).
- **Merkle batch anchoring** — Merkle-batch a set of evidence hashes into a single root with per-leaf proof paths. Served over REST, not as an A2A task: POST /anchors/batch (X-API-Key).
- **Amazon Ads Verdict Gate** — Allow, hold or forbid for an intended Amazon Ads MCP Server tool call (budgets, bids, campaigns), checked against the agency's mandate for that ad account befor
- **Leak canary for delegating agents** — One canary credential per counterparty, issued by the same path as POST /credentials/issue and indistinguishable from any other MolTrust credential. When a cana

## URLs
- Agent card: https://api.moltrust.ch/.well-known/agent-card.json
- Page (HTML): https://agenstry.com/agents/api.moltrust.ch
- Documentation: https://api.moltrust.ch/docs