VerityLayer

What is VerityLayer?

VerityLayer is a fail-closed verify-before-you-act trust gate for AI agents. It provides five tools for safety checks, operates keyless with pay-per-call via x402 (USDC on Base), and returns every verdict with an Ed25519-signed receipt.

How to use VerityLayer?

Run the MCP server with npx -y @veritylayer/mcp. The tools are invoked automatically by the MCP client; no manual configuration or API key is needed. For more details, visit veritylayer.dev.

Key features of VerityLayer

• Fail-closed, verify-before-you-act design for AI agents.
• Five tools: verify_fact, detect_injection, moderate_content, redact_pii, guard_action.
• Keyless authentication – no API key required.
• Pay-per-call via x402 using USDC on Base.
• Every verdict includes an Ed25519-signed receipt for trust.

Use cases of VerityLayer

• Fact-check AI agent outputs before executing actions.
• Detect prompt injections and jailbreak attempts in real time.
• Moderate content generated by AI responses.
• Redact personally identifiable information (PII) from text.
• Guard agent actions against unsafe or prohibited operations.

FAQ from VerityLayer

What is the pricing model?

Pay-per-call via x402 using USDC on the Base blockchain; no upfront costs or API keys needed.

How is trust enforced?

Every verdict is accompanied by an Ed25519-signed receipt, allowing independent verification of each decision.

What tools does VerityLayer provide?

Five tools: verify_fact, detect_injection, moderate_content, redact_pii, and guard_action.

Do I need to register for an API key?

No, VerityLayer is keyless – just run the MCP server and use the tools.

What blockchain does it use for payments?

Payments are processed on the Base blockchain via the x402 protocol using USDC.