Combine Common Commerce Protocol (UCP) with AI Brokers?

Agentic searching is shortly turning into mainstream.

Folks don’t simply need AI brokers to analysis merchandise anymore. They need brokers to truly purchase issues for them: examine choices, place orders, deal with funds, and full your entire transaction.

That’s the place issues began to interrupt.

At this time’s commerce stack is fragmented. Each service provider, platform, and fee supplier makes use of proprietary integrations. So even when an agent is wise sufficient to make choices, it struggles to behave at scale as a result of it has no frequent solution to discuss to those methods.

That is precisely the hole Google’s Common Commerce Protocol (UCP) is designed to repair.

UCP creates a standardized, safe method for AI brokers, retailers, platforms, and fee suppliers to speak. As an alternative of constructing customized integrations for each retailer or service, brokers can work together with commerce methods via a shared protocol, making agent-driven buying lastly sensible, interoperable, and scalable.

What Is the Common Commerce Protocol (UCP)? 

The Common Commerce Protocol is an open commerce customary that connects digital brokers with commerce methods. It gives a standard framework for locating merchandise, managing carts, executing funds, and dealing with post-purchase duties. UCP doesn’t substitute current e-commerce platforms or fee methods. As an alternative, it acts as a shared language that enables AI brokers, purposes, retailers, and fee suppliers to work together easily.

The Core Thought Behind UCP

UCP is an answer primarily to an integration problem. Up to now, every AI assistant or platform needed to depend on distinctive integrations with each service provider or commerce system. This technique was not scalable.

• A uniform commerce actions set
• Unambiguous position definitions for brokers, retailers, and fee processors
• Versatile schemas relevant throughout sectors
• This technique of working reduces the necessity for engineering dramatically and on the similar time permits faster innovation

Why UCP Issues?

At this time’s e-commerce ecosystem is very fragmented. Every procuring channel corresponding to web sites, cellular apps, and third celebration platforms requires customized integrations with each service provider. In consequence, a retailer promoting throughout a number of channels should handle many complicated integrations. This problem grows as AI procuring brokers turn out to be a standard method for individuals to buy.

UCP solves this by introducing a single customary protocol that covers your entire procuring journey, from product discovery to checkout and order administration. This simplifies integrations and permits the ecosystem to unlock a number of vital advantages.

• Unified integration: Reduces complicated N×N commerce integrations to a single integration level for AI brokers and interfaces.
• Shared language: Defines frequent schemas and APIs so all commerce methods can talk persistently finish to finish.
• Extensible, modular design: Makes use of modular elements that may evolve with out breaking current integrations.
• Safety-first method: Ensures safe, tokenized funds with verified person consent for each transaction.

For patrons, this implies smoother interactions and fewer deserted carts. Patrons can transfer shortly from searching or chatting to finishing a purchase order, typically with out re-entering particulars. As Google explains, UCP is designed so shoppers can confidently pay utilizing Google Pay, with fee and transport info already saved in Google Pockets.

Additionally Learn: High 10 Agentic AI Chrome Extensions

Why Google Launched UCP?

The commerce has slowly however certainly migrated into the realm of chat and robots. At this time the customers demand AI methods to behave as a substitute of merely informing. Google rolled out UCP to spearhead this transformation whereas nonetheless preserving the doorways open and the ecosystem secure. Agentic commerce is the time period used for AI methods which might be able to independently doing industrial work. Such brokers are capable of: 

• Search for and consider merchandise 
• Modify the choice in response to the person’s style 
• Execute purchases in a protected method 
• Deal with returns, give refunds, and supply help 

How Common Commerce Protocol (UCP) Works?

UCP works by breaking the commerce journey into a transparent sequence of actions that AI brokers can comply with. Every step represents a selected interplay, from discovering a product to finishing the transaction and dealing with what comes subsequent. Collectively, these steps outline how an agent strikes via a purchase order in a managed and predictable method. Let’s break this down and take a look at every step individually:

Step 1: Arrange the enterprise server and add pattern merchandise to your retailer

In an effort to make it simpler for companies to rise up and operating, Google has arrange a pattern repository. The repository comprises a Python server that’s prepared for use for internet hosting Enterprise APIs, together with a UCP SDK that gives pattern product information and reference implementations. These elements work collectively to assist the person visualize and perceive how a UCP-compliant enterprise server may be configured and examined.

Configuring the enterprise server:

mkdir sdk
git clone https://github.com/Common-Commerce-Protocol/python-sdk.git sdk/python
pushd sdk/python
uv sync
popd
git clone https://github.com/Common-Commerce-Protocol/samples.git 
cd samples/relaxation/python/server
uv sync

Utilizing a flower store for example, Google performs the position of the enterprise for demonstration functions. As well as, we offer a easy product database primarily based on SQLite that comprises the catalog information for the demo setting which is identical because the pattern information. This configuration permits the builders to make use of real looking product info for testing UCP workflows with out the necessity for an entire manufacturing database.

Step2: Put together your online business server to simply accept requests from brokers

Subsequent, begin the enterprise server that hosts the Enterprise APIs on port 8182 and connects to the demo product database. The server runs within the background so shopper purposes and AI brokers can join with out interruption. Run the command beneath to launch the enterprise server:

uv run server.py  
--products_db_path=/tmp/ucp_test/merchandise.db  
--transactions_db_path=/tmp/ucp_test/transactions.db  
--port=8182 & 
SERVER_PID=$! 

Step 3: Uncover enterprise capabilities along with your agent

Companies expose a JSON manifest at /.well-known/ucp that lists their obtainable providers and capabilities. This enables AI brokers to find options, endpoints, and fee configurations dynamically, with out counting on hard-coded integrations.

Now run the next command to let your agent uncover the enterprise providers and capabilities:

export SERVER_URL=http://localhost:8182 
export RESPONSE=$(curl -s -X GET $SERVER_URL/.well-known/ucp) 
echo $RESPONSE 
Response:  
{ 
"ucp": { 
"model": "2026-01-11", 
"providers": { "dev.ucp.procuring": { "model": "2026-01-11", "spec": "https://ucp.dev/specs/procuring", "relaxation": { "schema": "https://ucp.dev/providers/procuring/openapi.json", "endpoint": "http://localhost:8182/" } } }, 
"capabilities": [ 
{ "name": "dev.ucp.shopping.checkout", "version": "2026-01-11", "spec": "https://ucp.dev/specs/shopping/checkout", "schema": "https://ucp.dev/schemas/shopping/checkout.json" }, 
{ "name": "dev.ucp.shopping.discount", "version": "2026-01-11", "spec": "https://ucp.dev/specs/shopping/discount", "schema": "https://ucp.dev/schemas/shopping/discount.json", "extends": "dev.ucp.shopping.checkout" }, 
{ "name": "dev.ucp.shopping.fulfillment", "version": "2026-01-11", "spec": "https://ucp.dev/specs/shopping/fulfillment", "schema": "https://ucp.dev/schemas/shopping/fulfillment.json", "extends": "dev.ucp.shopping.checkout" } 
] 
}, 
"fee": { 
"handlers": [ 
{ "id": "shop_pay", "name": "com.shopify.shop_pay", "version": "2026-01-11", "spec": "https://shopify.dev/ucp/handlers/shop_pay", "config_schema": "https://shopify.dev/ucp/handlers/shop_pay/config.json", "instrument_schemas": [ "https://shopify.dev/ucp/handlers/shop_pay/instrument.json" ], "config": { "shop_id": "d124d01c-3386-4c58-bc58-671b705e19ff" } }, 
{ "id": "google_pay", "identify": "google.pay", "model": "2026-01-11", "spec": "https://instance.com/spec", "config_schema": "https://instance.com/schema", "instrument_schemas": [ "https://ucp.dev/schemas/shopping/types/gpay_card_payment_instrument.json" 
], "config": { "api_version": 2, "api_version_minor": 0, "merchant_info": { "merchant_name": "Flower Store", "merchant_id": "TEST", "merchant_origin": "localhost" }, "allowed_payment_methods": [ { "type": "CARD", "parameters": { "allowedAuthMethods": [ "PAN_ONLY", "CRYPTOGRAM_3DS" ], "allowedCardNetworks": [ "VISA", "MASTERCARD" ] }, "tokenization_specification": [ { "type": "PAYMENT_GATEWAY", "parameters": [ { "gateway": "example", "gatewayMerchantId": "exampleGatewayMerchantId" } ] } ] } ] } }, 
{ "id": "mock_payment_handler", "identify": "dev.ucp.mock_payment", "model": "2026-01-11", "spec": "https://ucp.dev/specs/mock", "config_schema": "https://ucp.dev/schemas/mock.json", "instrument_schemas": [ "https://ucp.dev/schemas/shopping/types/card_payment_instrument.json" ], "config": { "supported_tokens": [ "success_token", "fail_token" ] } } 
] 
} 
} 

Step 4: Invoke a checkout functionality along with your agent

Run this command to your agent to create a checkout session with the pattern merchandise:

export RESPONSE=$(curl -s -X POST "$SERVER_URL/checkout-sessions" -H 'Content material-Sort: utility/json' -H 'UCP-Agent: profile="https://agent.instance/profile"' -H 'request-signature: take a look at' -H 'idempotency-key: 0b50cc6b-19b2-42cd-afee-6a98e71eea87' -H 'request-id: 6d08ae4b-e7ea-44f4-846f-d7381919d4f2' -d '{"line_items":[{"item":{"id":"bouquet_roses","title":"Red Rose"},"quantity":1}],"purchaser":{"full_name":"John Doe","e mail":"[email protected]"},"foreign money":"USD","fee":{"devices":[],"handlers":[{"id":"shop_pay","name":"com.shopify.shop_pay","version":"2026-01-11","spec":"https://shopify.dev/ucp/handlers/shop_pay","config_schema":"https://shopify.dev/ucp/handlers/shop_pay/config.json","instrument_schemas":["https://shopify.dev/ucp/handlers/shop_pay/instrument.json"],"config":{"shop_id":"d124d01c-3386-4c58-bc58-671b705e19ff"}},{"id":"google_pay","identify":"google.pay","model":"2026-01-11","spec":"https://instance.com/spec","config_schema":"https://instance.com/schema","instrument_schemas":["https://ucp.dev/schemas/shopping/types/gpay_card_payment_instrument.json"],"config":{"api_version":2,"api_version_minor":0,"merchant_info":{"merchant_name":"Flower Store","merchant_id":"TEST","merchant_origin":"localhost"},"allowed_payment_methods":[{"type":"CARD","parameters":{"allowedAuthMethods":["PAN_ONLY","CRYPTOGRAM_3DS"],"allowedCardNetworks":["VISA","MASTERCARD"]},"tokenization_specification":[{"type":"PAYMENT_GATEWAY","parameters":[{"gateway":"example","gatewayMerchantId":"exampleGatewayMerchantId"}]}]}]}},{"id":"mock_payment_handler","identify":"dev.ucp.mock_payment","model":"2026-01-11","spec":"https://ucp.dev/specs/mock","config_schema":"https://ucp.dev/schemas/mock.json","instrument_schemas":["https://ucp.dev/schemas/shopping/types/card_payment_instrument.json"],"config":{"supported_tokens":["success_token","fail_token"]}}]}}') && echo $RESPONSE 

As quickly because the checkout session is created, your agent will achieve entry to a checkout id issued by the server that may additional be used for making updates to the checkout session:

RESPONSE: 
{ 
"ucp": { "model": "2026-01-11", "capabilities": [ { "name": "dev.ucp.shopping.checkout", "version": "2026-01-11" } ] }, 
"id": "cb9c0fc5-3e81-427c-ae54-83578294daf3", 
"line_items": [ { 
"id": "2e86d63a-a6b8-4b4d-8f41-559f4c6991ea", 
"item": { "id": "bouquet_roses", "title": "Bouquet of Red Roses", "price": 3500 }, 
"quantity": 1, 
"totals": [ { "type": "subtotal", "amount": 3500 }, { "type": "total", "amount": 3500 } ] 
} ], 
"purchaser": { "full_name": "John Doe", "e mail": "[email protected]" }, 
"standing": "ready_for_complete", 
"foreign money": "USD", 
"totals": [ { "type": "subtotal", "amount": 3500 }, { "type": "total", "amount": 3500 } ], 
"hyperlinks": [], 
"fee": { "handlers": [], "devices": [] }, 
"reductions": {} 
} 

Step 5: Apply reductions to the checkout request along with your agent

Run this command to allow your agent to use reductions to the checkout session, utilizing the checkout id from the earlier step:

export CHECKOUT_ID=$(echo $RESPONSE | jq -r '.id') && export LINE_ITEM_1_ID=$(echo $RESPONSE | jq -r '.line_items[0].id') && export RESPONSE=$(curl -s -X PUT "$SERVER_URL/checkout-sessions/$CHECKOUT_ID" -H 'Content material-Sort: utility/json' -H 'UCP-Agent: profile="https://agent.instance/profile"' -H 'request-signature: take a look at' -H 'idempotency-key: b9ecd4b3-0d23-4842-8535-0d55e76e2bad' -H 'request-id: 28e70993-e328-4071-91de-91644dc75221' -d "{"id":"$CHECKOUT_ID","line_items":[{"id":"$LINE_ITEM_1_ID","item":{"id":"bouquet_roses","title":"Red Rose"},"quantity":1}],"foreign money":"USD","fee":{"devices":[],"handlers":[]},"reductions":{"codes":["10OFF"]}}") && echo $RESPONSE | jq 

Your agent will obtain the next response with the low cost utilized:

RESPONSE:  
{ 
"ucp": { "model": "2026-01-11", "capabilities": [ { "name": "dev.ucp.shopping.checkout", "version": "2026-01-11" } ] }, 
"id": "cb9c0fc5-3e81-427c-ae54-83578294daf3", 
"line_items": [ { 
"id": "2e86d63a-a6b8-4b4d-8f41-559f4c6991ea", 
"item": { "id": "bouquet_roses", "title": "Bouquet of Red Roses", "price": 3500 }, 
"quantity": 1, 
"totals": [ { "type": "subtotal", "amount": 3500 }, { "type": "total", "amount": 3500 } ] } ], 
"purchaser": { "full_name": "John Doe", "e mail": "[email protected]" }, 
"standing": "ready_for_complete", 
"foreign money": "USD", 
"totals": [ { "type": "subtotal", "amount": 3500 }, { "type": "discount", "amount": 350 }, { "type": "total", "amount": 3150 } ], 
"hyperlinks": [], 
"fee": { "handlers": [], "devices": [] }, 
"reductions": { 
"codes": [ "10OFF" ], 
"utilized": [ { "code": "10OFF", "title": "10% Off", "amount": 350, "automatic": false, "allocations": [ { "path": "subtotal", "amount": 350 } ] } ] 
} 
} 

Key Parts of the Common Commerce Protocol

A UCP server, which is usually the service provider backend, reveals a number of providers. Each service corresponds to particular capabilities that may be distinguished among the many purposeful areas corresponding to product discovery or checkout. Widespread examples embody ucp.procuring.catalog, ucp.procuring.checkout, and ucp.procuring.orders. Retailers go for the capabilities they require, whereas the AI brokers will talk with the retailers as per the enabled capabilities.

Capabilities an Core Service

Extensions: Capabilities additionally allow using extensions to offer specialised capabilities. Extensions give retailers the possibility so as to add options like coupon reductions or subtle achievement strategies with out having to vary the first schemas.

Discovery

Every UCP enabled enterprise gives a manifest at https:///.well-known/ucp. This gives a listing of the providers obtainable, capabilities which might be supported, API endpoints, attainable variations, extensions, and particulars concerning the fee handlers.

Transports

UCP is just not restricted to a selected transport. The identical functionality payloads can transfer over REST, JSON RPC, or agent native protocols like Mannequin Context Protocol (MCP) and Agent2Agent (A2A) and even non-native ones.

Funds

UCP is built-in with varied fee suppliers via its pluggable fee handlers which embody Stripe, Google Pay, and Store Pay. The fee tokens are encrypted and routed throughout checkout.

Collectively, these components empower UCP to transform AI procuring dialogues into precise transactions. The conventional transaction is as follows:

1. The agent will get the service provider’s UCP manifest
2. It determines the related capabilities (as an example, checkout)
3. It calls these APIs together with the patron’s order particulars and chooses a fee handler
4. UCP takes care of the whole lot else (counting any reductions or achievement choices that have been mentioned)

Advantages for the Commerce Ecosystem 

• Retailers and Retailers: UCP lets retailers promote throughout AI-driven procuring surfaces with out shedding management over branding, information, or checkout. They continue to be the Service provider of Report whereas reaching customers via Google Search AI Mode, chatbots, and voice assistants utilizing a single integration.
• AI Platforms and Brokers: AI platforms like Google AI Mode, Gemini, and Microsoft Copilot can supply commerce options with out constructing customized integrations for every retailer. A unified API quickens service provider onboarding and allows scalable agent-driven commerce.
• Builders: UCP is open supply and developer pleasant, with clear documentation, SDKs, and reference implementations. Builders can construct utilizing acquainted instruments like REST and JSON and undertake solely the capabilities they want.
• Fee Suppliers: Fee suppliers can combine as soon as and work throughout many retailers utilizing UCP’s modular, tokenized fee circulation. This removes the necessity for platform-specific integrations.
• Customers: UCP allows customers to browse and purchase straight via AI assistants with out switching between apps or web sites, making a sooner and extra seamless procuring expertise.

Conclusion

The Common Commerce Protocol might reshape digital commerce within the AI period. It brings AI brokers, retailers, and funds collectively below one customary whereas preserving service provider management and enabling seamless procuring throughout chat, search, and voice. As AI assistants affect extra buy choices, UCP goals to maintain commerce open, safe, and scalable.

What’s your tackle agent-driven procuring? Share your ideas within the feedback beneath.

Good day! I am Vipin, a passionate information science and machine studying fanatic with a robust basis in information evaluation, machine studying algorithms, and programming. I’ve hands-on expertise in constructing fashions, managing messy information, and fixing real-world issues. My objective is to use data-driven insights to create sensible options that drive outcomes. I am desirous to contribute my expertise in a collaborative setting whereas persevering with to be taught and develop within the fields of Knowledge Science, Machine Studying, and NLP.