Agentic searching is rapidly changing into mainstream.
Individuals don’t simply need AI brokers to analysis merchandise anymore. They need brokers to truly purchase issues for them: evaluate choices, place orders, deal with funds, and full your complete transaction.
That’s the place issues began to interrupt.
At the moment’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 selections, it struggles to behave at scale as a result of it has no frequent solution to speak to those techniques.
That is precisely the hole Google’s Common Commerce Protocol (UCP) is designed to repair.
UCP creates a standardized, safe manner for AI brokers, retailers, platforms, and fee suppliers to speak. As a substitute of constructing customized integrations for each retailer or service, brokers can work together with commerce techniques 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 commonplace that connects digital brokers with commerce techniques. It gives a typical framework for locating merchandise, managing carts, executing funds, and dealing with post-purchase duties. UCP doesn’t substitute present e-commerce platforms or fee techniques. As a substitute, 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. Prior to now, every AI assistant or platform needed to depend on distinctive integrations with each service provider or commerce system. This methodology was not scalable.
- A uniform commerce actions set
- Unambiguous function definitions for brokers, retailers, and fee processors
- Versatile schemas relevant throughout sectors
- This methodology of working reduces the necessity for engineering dramatically and on the identical time permits faster innovation
Why UCP Issues?
At the moment’s e-commerce ecosystem is extremely fragmented. Every purchasing channel corresponding to web sites, cell apps, and third celebration platforms requires customized integrations with each service provider. Consequently, a retailer promoting throughout a number of channels should handle many advanced integrations. This problem grows as AI purchasing brokers turn into a typical manner for folks to buy.
UCP solves this by introducing a single commonplace protocol that covers your complete purchasing journey, from product discovery to checkout and order administration. This simplifies integrations and permits the ecosystem to unlock a number of necessary advantages.
- Unified integration: Reduces advanced N×N commerce integrations to a single integration level for AI brokers and interfaces.
- Shared language: Defines frequent schemas and APIs so all commerce techniques can talk constantly finish to finish.
- Extensible, modular design: Makes use of modular elements that may evolve with out breaking present integrations.
- Safety-first strategy: Ensures safe, tokenized funds with verified consumer consent for each transaction.
For purchasers, this implies smoother interactions and fewer deserted carts. Consumers can transfer rapidly from searching or chatting to finishing a purchase order, typically with out re-entering particulars. As Google explains, UCP is designed so customers can confidently pay utilizing Google Pay, with fee and transport data already saved in Google Pockets.
Additionally Learn: Prime 10 Agentic AI Chrome Extensions
Why Google Launched UCP?
The commerce has slowly however certainly migrated into the realm of chat and robots. At the moment the customers demand AI techniques to behave as a substitute of merely informing. Google rolled out UCP to spearhead this transformation whereas nonetheless conserving the doorways open and the ecosystem steady. Agentic commerce is the time period used for AI techniques which can be able to independently doing business work. Such brokers are in a position to:
- Search for and consider merchandise
- Modify the choice in keeping with the consumer’s style
- Execute purchases in a protected method
- Deal with returns, give refunds, and supply assist
How Common Commerce Protocol (UCP) Works?
UCP works by breaking the commerce journey into a transparent sequence of actions that AI brokers can observe. 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 manner. 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
To be able to make it simpler for companies to rise up and working, Google has arrange a pattern repository. The repository accommodates 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 consumer visualize and perceive how a UCP-compliant enterprise server will 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 syncUtilizing a flower store for instance, Google performs the function of the enterprise for demonstration functions. As well as, we offer a easy product database primarily based on SQLite that accommodates the catalog information for the demo atmosphere which is identical because the pattern information. This configuration permits the builders to make use of lifelike product data for testing UCP workflows with out the necessity for an entire manufacturing database.
Step2: Put together your online business server to just 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 consumer 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=$! Step 3: Uncover enterprise capabilities together with your agent
Companies expose a JSON manifest at /.well-known/ucp that lists their accessible companies and capabilities. This enables AI brokers to find options, endpoints, and fee configurations dynamically, with out counting on hard-coded integrations.
Now run the next command to let your agent uncover the enterprise companies and capabilities:
export SERVER_URL=http://localhost:8182
export RESPONSE=$(curl -s -X GET $SERVER_URL/.well-known/ucp)
echo $RESPONSE
Response:
{
"ucp": {
"model": "2026-01-11",
"companies": { "dev.ucp.purchasing": { "model": "2026-01-11", "spec": "https://ucp.dev/specs/purchasing", "relaxation": { "schema": "https://ucp.dev/companies/purchasing/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 together with your agent
Run this command on 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: software/json' -H 'UCP-Agent: profile="https://agent.instance/profile"' -H 'request-signature: check' -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","electronic mail":"[email protected]"},"forex":"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 $RESPONSE As quickly because the checkout session is created, your agent will acquire entry to a checkout id issued by the server that may additional be used for making updates to the checkout session:
RESPONSE:
{
"ucp": { "model": "2026-01-11", "capabilities": [ { "name": "dev.ucp.shopping.checkout", "version": "2026-01-11" } ] },
"id": "cb9c0fc5-3e81-427c-ae54-83578294daf3",
"line_items": [ {
"id": "2e86d63a-a6b8-4b4d-8f41-559f4c6991ea",
"item": { "id": "bouquet_roses", "title": "Bouquet of Red Roses", "price": 3500 },
"quantity": 1,
"totals": [ { "type": "subtotal", "amount": 3500 }, { "type": "total", "amount": 3500 } ]
} ],
"purchaser": { "full_name": "John Doe", "electronic mail": "[email protected]" },
"standing": "ready_for_complete",
"forex": "USD",
"totals": [ { "type": "subtotal", "amount": 3500 }, { "type": "total", "amount": 3500 } ],
"hyperlinks": [],
"fee": { "handlers": [], "devices": [] },
"reductions": {}
} Step 5: Apply reductions to the checkout request together with your agent
Run this command to allow your agent to use reductions to the checkout session, utilizing the checkout id from the earlier step:
export CHECKOUT_ID=$(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: software/json' -H 'UCP-Agent: profile="https://agent.instance/profile"' -H 'request-signature: check' -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}],"forex":"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", "electronic mail": "[email protected]" },
"standing": "ready_for_complete",
"forex": "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 Elements of the Common Commerce Protocol
A UCP server, which is usually the service provider backend, reveals a number of companies. Each service corresponds to particular capabilities that may be distinguished among the many practical areas corresponding to product discovery or checkout. Frequent examples embody ucp.purchasing.catalog, ucp.purchasing.checkout, and ucp.purchasing.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 supply specialised capabilities. Extensions give retailers the choice so as to add options like coupon reductions or refined achievement strategies with out having to alter the first schemas.
Discovery
Every UCP enabled enterprise gives a manifest at https://
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 numerous 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 elements empower UCP to transform AI purchasing dialogues into precise transactions. The traditional transaction is as follows:
- The agent will get the service provider’s UCP manifest
- It determines the related capabilities (as an example, checkout)
- It calls these APIs together with the patron’s order particulars and chooses a fee handler
- UCP takes care of every little thing else (counting any reductions or achievement choices that had been mentioned)
Advantages for the Commerce Ecosystem
- Retailers and Retailers: UCP lets retailers promote throughout AI-driven purchasing surfaces with out dropping management over branding, information, or checkout. They continue to be the Service provider of Document 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 accelerates 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.
- Cost Suppliers: Cost suppliers can combine as soon as and work throughout many retailers utilizing UCP’s modular, tokenized fee stream. This removes the necessity for platform-specific integrations.
- Customers: UCP allows customers to browse and purchase immediately via AI assistants with out switching between apps or web sites, making a sooner and extra seamless purchasing expertise.
Conclusion
The Common Commerce Protocol might reshape digital commerce within the AI period. It brings AI brokers, retailers, and funds collectively underneath one commonplace whereas preserving service provider management and enabling seamless purchasing throughout chat, search, and voice. As AI assistants affect extra buy selections, UCP goals to maintain commerce open, safe, and scalable.
What’s your tackle agent-driven purchasing? Share your ideas within the feedback beneath.
Hiya! 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 atmosphere whereas persevering with to be taught and develop within the fields of Knowledge Science, Machine Studying, and NLP.
Login to proceed studying and revel in expert-curated content material.
