Otr Protocol

OTR Protocol

The merchant trust layer for AI agent commerce

Deterministic, verifiable, open-source merchant trust scoring for the agentic economy

Protocol v4.1

Specification • Scoring Algorithm • Quick Start • Packages • Contributing

---

The Problem

AI agents are increasingly making purchase decisions on behalf of consumers. The agentic commerce stack is taking shape -- but there is a critical missing layer:

┌──────────────────────────────────────────────────────────────────┐

│ AI Agent Commerce Protocol Stack │ ├──────────────────────────────────────────────────────────────────┤ │ │ │ Visa TAP ·············· Agent Identity Verification │ │ Google UCP ············ Structured Data Exchange │ │ Stripe ACP ············ Payment Processing │ │ │ │ ┌───────────────────────────────────────────────────────────┐ │ │ │ OTR Protocol ····· MERCHANT TRUST VERIFICATION ◀━━━━━ │ │ │ │ "Is this merchant safe to buy from?" │ │ │ └───────────────────────────────────────────────────────────┘ │ │ │ │ Visa TAP answers "Who is the AI agent?" │ │ Google UCP answers "What products are available?" │ │ Stripe ACP answers "How do I pay?" │ │ OTR answers "Should I trust this merchant?" ◀━━ ONLY OTR │ │ │ └──────────────────────────────────────────────────────────────────┘

Without OTR, AI agents operate blind -- unable to distinguish a legitimate retailer from a sophisticated scam site. This exposes consumers to fraud and erodes trust in the entire agentic commerce ecosystem.

The Solution

OTR (Open Trust Registry) provides deterministic, verifiable merchant trust scores using 6 verification dimensions, a 10-layer anti-fraud pipeline (Layer 0: Google Web Risk one-vote veto + Layers 1-9: core detection engine), and three-layer immutable audit trail. It is fully open-source (MIT), machine-readable, and designed from the ground up for AI agent consumption.

Key Properties

• Deterministic -- Same inputs always produce identical outputs. Any validator can reproduce any score.
• Verifiable -- All data sources are publicly accessible. No hidden factors or proprietary signals.
• Unforgeable -- Verification dimension weighted at 40% in public assessment. SEC filings, Wikidata entries, and 10-year domain age cannot be faked.
• Tamper-proof -- SHA-256 hash chain + Base L2 blockchain anchoring + IPFS monthly snapshots.
• Fair -- No pay-for-trust. Scores reflect behavior, not subscription level.
• Category-aware -- Three site categories (ecommerce / saas / non_commerce) with tailored scoring weights.
• Safety-first -- Google Web Risk Layer 0 one-vote veto: flagged domains get score=0, status SUSPENDED.

Quick Start

# Verify any merchant instantly

npx @otr-protocol/validator verify nike.com

Output:

┌──────────────────────────────────────────────┐

│ nike.com GOLD │

│ Trust Score: 88/100 Category: ecommerce │

│ OTR-ID: OTR-1C-7F3A2B9E4D1C-K4 │

│ │

│ Verification: 85 ██████████████░░ │

│ Security: 80 █████████████░░░ │

│ Governance: 72 ████████████░░░░ │

│ Transparency: 75 ████████████░░░░ │

│ Data Quality: 65 ██████████░░░░░░ │

│ Fulfillment: -- (COLD mode) │

└──────────────────────────────────────────────┘

For AI Agents (MCP Server)

The OTR MCP Server uses the standard Model Context Protocol and works with all MCP-compatible clients.

Claude Desktop / Claude Code -- add to claude_desktop_config.json:

{

"mcpServers": { "otr": { "command": "npx", "args": ["@otr-protocol/mcp-server"] } } }

Cursor / Windsurf / Cline -- same configuration in .cursor/mcp.json or equivalent. Any client implementing the MCP specification works out of the box.

Now any AI agent can verify merchants in natural language:

*"Is nike.com trustworthy?"* --> OTR returns trust score 88/100, badge GOLD, and a 6-dimension breakdown (Verification, Security, Governance, Transparency, DataQuality, Fulfillment) with evidence sources.

Two MCP Tools — One Call = Complete Answer

Design philosophy: AI agents should get everything they need in a single tool call. verify_merchant returns trust assessment + purchase capabilities + links + policy URLs + data freshness — no need to chain multiple calls.

TypeScript SDK

import { OtrClient } from "@otr-protocol/sdk";

const otr = new OtrClient(); const result = await otr.verify("nike.com");

console.log(result.trustScore); // 88 console.log(result.badge); // "GOLD" console.log(result.dimensions); // { verification: 85, security: 80, ... }

// Search the registry const results = await otr.search("electronics", { minScore: 70 });

Core Scoring Engine

import { calculateTrustScore } from "@otr-protocol/core";

// Deterministic: same inputs always produce identical outputs const result = calculateTrustScore({ hasSecFiling: true, hasStockSymbol: true, stockExchange: "NYSE", hasWikidataId: true, trancoRank: 500, domainAgeYears: 15, // ... 40+ evidence fields });

console.log(result.trustScore); // 88 console.log(result.badge); // "GOLD" console.log(result.tier); // "TIER_4"

Architecture

                         ┌─────────────────────────────────┐

│ AI Agent / Application │ │ "Should I buy from example.com?" │ └──────────────┬──────────────────┘ │ ┌───────────────────┼───────────────────┐ │ │ │ ┌─────▼─────┐ ┌──────▼──────┐ ┌──────▼──────┐ │ MCP Server │ │ REST API │ │ SDK │ │ (stdio) │ │ /api/otr │ │ npm pkg │ └─────┬──────┘ └──────┬──────┘ └──────┬──────┘ │ │ │ └───────────────────┼───────────────────┘ │ ┌──────────────▼──────────────┐ │ OTR Scoring Engine │ │ @otr-protocol/core │ │ │ │ ┌─────────────────────────┐ │ │ │ 6 Dimension Evaluators │ │ │ │ Verification | Security │ │ │ │ Governance | Transparency│ │ │ │ DataQuality | Fulfillment│ │ │ └─────────────────────────┘ │ │ ┌─────────────────────────┐ │ │ │ 10-Layer Anti-Fraud │ │ │ │ Domain Age | SSL | DNS │ │ │ │ Pattern | Tranco | ... │ │ │ └─────────────────────────┘ │ │ ┌─────────────────────────┐ │ │ │ Brand Fast-Track │ │ │ │ SEC + Tranco + Wikidata │ │ │ └─────────────────────────┘ │ └──────────────┬──────────────┘ │ ┌─────────────────────────┼─────────────────────────┐ │ │ │ ┌────────▼────────┐ ┌──────────▼──────────┐ ┌─────────▼─────────┐ │ Public Data │ │ Merchant Bridge │ │ Immutable Audit │ │ Sources │ │ (Verified Only) │ │ Trail │ │ │ │ │ │ │ │ SEC EDGAR │ │ Product Catalog │ │ SHA-256 Hash │ │ Wikidata │ │ Order Data (agg) │ │ Chain │ │ Tranco List │ │ Delivery Metrics │ │ Base L2 Anchoring │ │ DNS Records │ │ Tracking Numbers │ │ IPFS Snapshots │ │ SSL Certs │ │ (desensitized) │ │ │ │ Finnhub.io │ │ │ │ │ │ Google Web Risk │ │ │ │ │ │ Website Scan │ │ │ │ │ └─────────────────┘ └──────────────────────┘ └───────────────────┘

How Scoring Works

6 Trust Dimensions

Weights vary by site category:

What Each Dimension Measures

| Verification (V) | Is this a real, registered business? SSL certificate type, GLEIF LEI, Wikidata entity,