Enter access code to continue
Incorrect access code
Hackathon Resource

Your agent can pay.
Can it prove who it is?

x402 solves payments for AI agents. MolTrust solves identity. Add W3C Verifiable Credentials to your project in under 10 minutes — free endpoints, no API key, no signup required.

Three questions your agent can't answer yet

Question 1

When your agent calls another agent or API, how does the receiving side know it's not a bot or a malicious actor?

Question 2

If your agent makes a purchase, books a service, or places a prediction — how do you prove it was authorized to do so?

Question 3

If something goes wrong in an autonomous workflow, can you produce a tamper-evident audit trail of which agent did what?

The identity layer for AI agents

MolTrust issues W3C Verifiable Credentials to AI agents. Each credential is cryptographically signed, anchored on Base blockchain, and verifiable by any standards-compliant resolver — without contacting MolTrust. It is the trust layer that makes agent-to-agent interactions auditable and fraud-resistant.

Think of it as a passport system for AI agents. An agent with a MolTrust credential can prove its identity, capability, and authorization to any other agent or platform — in a single API call.

Standards used: W3C DID v1.0, W3C Verifiable Credentials v2.0, Ed25519 signatures, x402 payments on Base L2.

Integrate in 3 steps

The free audit endpoint requires no API key, no signup, and no wallet. Your agent gets a trust score in seconds.

1
Audit your agent's SKILL.md (free, instant)

Point the auditor at a GitHub URL containing a SKILL.md file. Gets scored for prompt injection, data exfiltration patterns, scope violations, and metadata completeness.

# No API key needed — just point at your GitHub SKILL.md
curl "https://api.moltrust.ch/guard/skill/audit?url=https://github.com/your-org/your-agent"

# Response in <2 seconds:
{
  "audit": {
    "score": 87,
    "findings": [],
    "auditorVersion": "1.0.0"
  },
  "passed": true
}
2
Issue a Verifiable Credential ($2–5 USDC via x402)

Your agent pays per call — no subscription, no API key.

import requests

vc = requests.post(
    "https://api.moltrust.ch/guard/vc/skill/issue",
    headers={"X-Payment": "<x402-proof>"},
    json={"did": "did:web:your-agent.com", "skill": "data-analysis"}
).json()["credential"]

# W3C VC, Ed25519 signed, Base-anchored
# Verifiable by anyone, forever
3
Verify any agent credential (free)

Any platform can verify — no MolTrust dependency.

curl https://api.moltrust.ch/guard/skill/verify/<credential-hash>

# Returns: valid, issuer DID, base_anchor tx, timestamp

6 verticals, ready to use

Each vertical has its own credential schema and free endpoints. Pick what fits your hackathon project.

VerifiedSkillCredential
Skill Verification FREE audit
Audits your agent's SKILL.md for prompt injection, data exfiltration, and scope violations. Proves your agent is safe before it touches anything.
AgentCredential
Core Identity
Base DID registration + on-chain anchor. The foundation credential — every agent needs one.
PredictionTrackCredential
Prediction Markets FREE lookup
Link a Polymarket wallet to a DID. Prove track record on-chain — not self-reported.
BuyerAgentCredential
Shopping Agent
Merchant-verified authorization for shopping agents. Prevents unauthorized purchases.
TravelAgentCredential
Travel Delegation
10-step delegation chain verification. Proves an agent is authorized to book on behalf of a user.
SalesguardCredential
Brand Protection FREE verify
Verify product provenance in one GET call. Stops AI agents from buying or selling counterfeits.

Start with these — no API key needed

All free endpoints work immediately. Paid endpoints ($1–5 USDC via x402) unlock credential issuance.

EndpointWhat it does
GET/guard/healthAPI status check
GET/guard/skill/audit?url=<github-url>SKILL.md security audit — prompt injection, scope, exfiltration checks
GET/guard/api/agent/score-free/:addrFree trust score for any wallet address
POST/guard/prediction/wallet-linkLink wallet to W3C DID {"address","name","platform"}
GET/guard/prediction/wallet/:addrVerified prediction track record
GET/guard/salesguard/verify/:product_idProduct provenance check
GET/guard/skill/verify/:hashVerify any issued credential

Ready to add agent identity?

Full API docs, code examples, and MCP tools for all 6 verticals. 33 tools, 69 tests passing.

Questions? @moltrust on X