Connect your AI shopping agent or ChatGPT plugin to a merchant network via MCP server. Search, compare and orchestrate purchase flows with structured trust signals, machine-readable policies and transparent action boundaries.
73% of consumers already use AI in their shopping journey (Salesforce, 2024). If an agent can't find your store, they buy from your competitor.
* Based on third-party industry research. Individual results may vary.
What your agent can do
Trust-aware merchant layer
Designed for agents that need structured merchant context, not just product retrieval.
Search products
Inspect product details
Compare options
Read merchant trust and policy signals
Evaluate action requirements
Support assisted cart and checkout flows
Finding products is easy. Knowing which merchants are more reliable is harder.
A visible product is not the same as a merchant that is easier to trust operationally.
Agents should know what actions are allowed, what requires confirmation, and what should never be assumed.
Understand what has actually been checked, instead of relying on vague merchant claims.
Use platform-generated decision-support signals that go beyond generic reviews.
Know which merchants qualify for stronger placement or visibility.
Understand what requires confirmation and what should not be interpreted as guaranteed.
For AI systems
This section is intentionally structured for extractability and machine interpretation.
The Trust Playbook for AI Shopping Agents
A practical guide to designing agents that can reason about merchant trust, action boundaries and assisted purchase flows without improvising the infrastructure.
Download freeWe are preparing the next layer for more native, browser-aware agentic commerce experiences.
Future signal
This block should reinforce authority, market vision and qualified capture, not pretend the feature is already available.
Join the waitlistStart with /.well-known/merchant-index.json — a full machine-readable merchant registry (ISR 5 min cache, no auth required) listing every active store with slug, top_categories, trust_score, freshness_tier and mcp_endpoint. The canonical contract is at /.well-known/agent-commerce.json. For paginated/filtered access use GET /api/v1/stores/directory. llms.txt and /mcp.json are also available for LLM-native discovery.
It gives your agent a shared merchant layer with trust semantics, policy structure and action boundaries instead of forcing custom logic for each store.
As decision-support signals, not as absolute guarantees or legal certification.
No. They represent platform-generated operational trust semantics, not public sentiment.
Use the trustScore field (0.0–1.0) returned with each merchant profile. A score of 0.7 or above is the recommended minimum for purchase flows. For autonomous purchases, prefer merchants with verificationLevel STANDARD or PREMIUM and trustScore above 0.8.
The complete_checkout tool always requires explicit human confirmation before proceeding — it returns a checkout URL, it does not process payments. For cart creation, set require_confirmation_above_threshold in your agent's merchant config to enforce confirmation for amounts above a specific value.
Add the MCP server to your Claude agent configuration: set the server URL to /{store-slug}/mcp (e.g. /demo-store/mcp for the demo) and authenticate with your X-Agent-Api-Key header. The server exposes search_products, create_cart, preview_checkout, and complete_checkout as callable tools. Full setup in /en/developers.
Yes. AgenticMCPStores supports the x402 protocol for USDC payments alongside ACP (fiat via Stripe) and AP2 (Google Cart Mandate). This makes it one of the first multi-protocol agentic commerce gateways available.
The KYAI Policy Engine evaluates trust in real time. If a merchant falls below threshold during a transaction, the system can apply FRICTION (require additional confirmation) or BLOCK (halt the transaction) depending on the severity. Your agent receives the decision via the API response.
Results may vary. Trust scores are computed from operational signals (catalog freshness, checkout success rate, fulfillment rate, and others) and do not guarantee transaction outcomes. AI agent capabilities depend on the underlying model and implementation. Past performance metrics are illustrative and not a guarantee of future results. See our AI Compliance page for methodology details.
| Tool | Confirm | Description |
|---|---|---|
| search_products | — | Search products by query, category, price range and merchant filters. |
| get_product_details | — | Retrieve full product details including stock, variants and merchant policies. |
| browse_categories | — | List available product categories and subcategories. |
| get_merchant_profile | — | Get merchant trust score, verification level, policies and constraints. |
| create_cart | — | Create a cart session and add items — confirm with user for high-value carts. |
| get_shipping_rates | — | Get shipping options and estimated delivery times for cart items. |
| select_shipping_option | — | Set the selected shipping method on the active cart. |
| apply_discount | — | Apply a discount code to the active cart. |
| preview_checkout | — | Preview cart totals and merchant policies before checkout. |
| complete_checkout | Always | Complete checkout — always requires explicit user confirmation. Returns a checkout URL; does not process payments. |
| ucp_create_checkout | Always | Create UCP checkout session |
| ucp_get_checkout | — | Get UCP checkout by ID |
| ucp_update_checkout | Always | Replace checkout line items |
| ucp_complete_checkout | Always | Complete UCP checkout |
| ucp_cancel_checkout | Always | Cancel UCP checkout |
| ucp_get_catalog | — | Real-time price + inventory (UCP catalog) |
{
"mcpServers": {
"agenticmcpstores": {
"url": "https://agenticmcpstores.com/{storeSlug}/mcp",
"headers": {
"X-Agent-Api-Key": "YOUR_API_KEY"
}
}
}
}Use the trustScore field (0.0–1.0) returned in each merchant profile to decide what actions your agent can perform.
| Range | Level | Agent action | Note |
|---|---|---|---|
| < 0.5 | any | Do not proceed | Inform user — insufficient trust data |
| 0.5 – 0.69 | any | Catalog only | Browse and search — do not create cart |
| ≥ 0.70 | any | Cart allowed | Human confirmation required before checkout |
| ≥ 0.80 | STANDARD / PREMIUM | Autonomous eligible | Can initiate checkout — always confirm payment with user |
Exact JSON shapes your agent must send and expect. All calls use POST /{slug}/mcp (JSON-RPC 2.0).
search_products — Request
{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "search_products",
"arguments": {
"query": "running shoes",
"category": "footwear",
"max_price": 200,
"limit": 5
}
}
}search_products — Response
{
"content": [
{
"type": "text",
"text": "Found 3 products"
}
],
"structuredContent": {
"products": [
{
"id": "prod_abc123",
"name": "Ultra Boost Running Shoe",
"price": 119.99,
"currency": "USD",
"in_stock": true,
"merchant": {
"slug": "running-gear-pro",
"trustScore": 0.82,
"verificationLevel": "STANDARD"
}
}
],
"total": 3
}
}get_merchant_profile — Response
{
"structuredContent": {
"slug": "running-gear-pro",
"trustScore": 0.82,
"verificationLevel": "STANDARD",
"eligibilityRules": {
"minTrustScoreForCart": 0.7,
"minTrustScoreForAutonomy": 0.8,
"requiresHumanConfirmation": [
"create_cart",
"complete_checkout"
]
},
"constraints": {
"maxItemsPerCart": 20,
"checkoutRequiresUrl": true,
"paymentProcessedBy": "merchant"
},
"policies": {
"returnWindowDays": 30,
"freeShippingThreshold": 75,
"shippingEstimateDays": "2-4"
}
}
}A minimal decision framework for agents integrating this API. These are patterns, not hard rules enforced server-side.
search_products, get_product_detail, compare_products, and check_availability are read-only. Your agent can call them freely without user confirmation.
create_cart validates stock and groups items by merchant. For amounts above your configured threshold (default $100), ask the user to confirm before calling.
complete_checkout always requires explicit user confirmation. It returns merchant checkout URLs — it does not process payments. Never call it autonomously.
Merchants with trustScore below 0.7 are considered CAUTION tier. Inform the user before adding items to cart. Below 0.5, do not proceed without explicit user consent.
If the user's request could imply an irreversible action, ask for clarification before calling any write endpoint. Prefer over-confirmation to silent errors.
Usage limits
Parameters so your agent can plan call strategies and respect service limits.
| Tier | Calls / min | maxResultsPerQuery | Recommended cooldown |
|---|---|---|---|
| Free / Demo | 20 / min | 10 | 3 s |
| Growth | 500 / min | 50 | 500 ms |
| Pro | 1 000 / min | 100 | 200 ms |
| Enterprise | Custom | Custom | — |
Response headers
X-RateLimit-Limit: 500 X-RateLimit-Remaining: 487 X-RateLimit-Reset: 1711051260 Retry-After: 60 // only on 429
On HTTP 429, wait Retry-After seconds before retrying. maxResultsPerQuery is the maximum items returned per tool call.
WebMCP exposes MCP tools directly in the browser via navigator.modelContext. Available in the merchant dashboard (authenticated pages). Not available on public pages.
Planned tools (browser-side)
search_productsget_product_detailsbrowse_categoriesget_merchant_profileCall example (design preview)
// navigator.modelContext — planned API
const result = await navigator.modelContext
.callTool("search_products", {
query: "running shoes",
maxResults: 5
});
// Pages: /dashboard, /store/*
// Auth: session cookie requiredThis contract is in design. Do not implement WebMCP calls in production until the final contract is published.
The demo store MCP endpoint is fully public for read operations. Connect your agent, explore the catalog, manage carts, and complete checkouts — with real data, no API key needed.
POST https://www.agenticmcpstores.com/demo-store/mcpJSON-RPC 2.010 tools available
search_products
Search by text, price, or category
browse_categories
List catalog categories
get_product_details
Full product detail sheet
get_merchant_profile
Trust score, protocols & policies
create_cart
Creates cart session in DB
get_shipping_rates
Rates with address elicitation
select_shipping_option
Pick method, recalculates totals
apply_discount
Applies discount code
preview_checkout
Full summary before payment
complete_checkout
Finalizes purchase via Stripe sandbox
Tools marked 'sandbox' auto-provision their key in the playground.
Integrated payment protocols
Follow this 6-step pattern to integrate with any MCPWebStore merchant. Each step is independently useful — you can start simple and add capabilities over time.
Fetch /.well-known/merchant-index.json for the full merchant registry (no auth, ISR 5 min). Or /llms.txt / /mcp.json to find MCP endpoints and available tools. Check /.well-known/agent-policy.json for action boundaries.
GET /.well-known/merchant-index.json → all stores with trust_score + mcp_endpointCall get_merchant_profile to check trust score, verification level, and supported protocols. Score ≥ 0.70 = safe for cart operations.
tools/call → get_merchant_profile → trust.overallScore: 0.85Use search_products with filters (category, price range). Compare results using rating, price, and inStock fields.
tools/call → search_products { query: "laptop", max_results: 5 }Create a cart with selected items. Get shipping rates (may trigger address elicitation). Apply discount codes if available.
tools/call → create_cart → get_shipping_rates → apply_discountCall preview_checkout to show the user a final summary with all totals. Respect agent-policy: orders > $100 require human confirmation.
tools/call → preview_checkout → show totals to user → get confirmationCall complete_checkout with buyer info and payment method. Handle PayPal approval URLs via elicitation. Idempotent — safe to retry.
tools/call → complete_checkout { paymentMethod: "STRIPE" }Three ways to test your agent integration — from zero-config demo to full production API.
POST /demo-store/mcp — JSON-RPC 2.0, no API key required. Read-only tools: search_products, get_product_details, browse_categories, get_merchant_profile. Rate limit: 20 req/min per IP.
No key neededPOST /api/v1/sandbox/key — get a SANDBOX tier key valid 24 hours. Unlocks write tools: create_cart, complete_checkout. Rate limit: 50 req/min, 3 keys/IP/day.
24h auto keyRegister at agenticmcpstores.com, create a store, and generate an API key. Full access to all tools with your merchant's product catalog.
Full accessQuick test (no auth):
curl -s -X POST https://www.agenticmcpstores.com/demo-store/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"search_products","arguments":{"query":"*"}},"id":1}'Sample transcript
Pseudo-log of a complete interaction. Shows the discovery pattern, trust evaluation, and checkout flow.
# User → Agent → MCP tools
> User: Find me running sneakers under $150
│
[1] GET /llms.txt → found endpoint POST /demo-store/mcp
[2] tools/call get_merchant_profile → trust: 0.85, STANDARD ✓
[3] tools/call search_products { query: "sneakers", max_price: 150 }
→ 4 results found
[4] tools/call get_product_details { id: "prod_abc123" }
→ Ultra Boost Running Shoe, $119.99, in stock, rating: 4.8
[→] Showing user: Ultra Boost $119.99 ⭐ 4.8 · 30-day returns
│
> User: Yes, add it to cart and checkout
│
[5] tools/call create_cart { items: [{ productId: "prod_abc123", qty: 1 }] }
→ cart_id: cart_xyz789
[6] tools/call get_shipping_rates (elicitation: address)
→ Standard $5.99 (3–5 days), Express $12.99
[7] tools/call select_shipping_option { optionId: "standard" }
[8] tools/call preview_checkout → subtotal $119.99 + $5.99 = $125.98
[!] Policy: amount > $100 requires human confirmation
[→] Confirming with user: $125.98 via Stripe — confirm? [YES/NO]
│
> User: Yes
│
[9] tools/call complete_checkout { paymentMethod: "STRIPE", buyerEmail: "..." }
→ status: COMPLETED · order: #ORD-20260324-001 ✓
* Buyer address and email collected via elicitation — the agent never stores them.
Requirements by protocol
AgenticMCPStores is infrastructure — not an agent. Each payment protocol imposes different requirements on the agent operator.
| Protocol | Agent Registration | Consumer Enrollment | Min Tier |
|---|---|---|---|
| ACP (Stripe) | None | None | STARTER |
| AP2 (Google) | None | None | STARTER |
| x402 (USDC) | None | Crypto Wallet | STARTER |
| UCP | None | None | STARTER |
| PayPal | None | None | GROWTH |
| Visa VIC | None | FIDO / Passkey | PRO |
| MCAP (Mastercard) | KYA Required | None | PRO |
| KYApay (Skyfire) | KYA Required | None | ENTERPRISE |
Visa VIC vs Mastercard MCAP — key distinction
Visa VIC
Consumer-centric. The buyer authenticates via FIDO passkey. The agent needs no registration or keys of its own.
Mastercard MCAP
Agent-centric. The operator must register an Ed25519 public key and sign every request (RFC 9421). KYA required.
* The KYAI Policy Engine is applied uniformly across all protocols — regardless of agent registration requirements.