Know of an official OpenAPI document? Contribute it →
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Centra Checkout API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcentra.com%2Fcentra" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcentra.com%2Fcentra" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Centra Checkout API.
Read the current selection and add items and lines to it
Adjust the quantity on a selection line
Place an order and submit a payment
Register and log in a customer
List reference data such as markets, countries, and warehouses
Patterns agents use Centra Checkout API for, with concrete tasks.
★ AI agent headless checkout
An AI shopping agent can build a cart and place an order on a Centra storefront on demand. Through Jentic the agent searches by intent and the API token never enters its prompt context, so a checkout assistant can add items and order without a hand-built integration.
Use Jentic to search 'add an item to a cart', call POST /items/{item} to add it, then POST /orders followed by POST /payment to place and pay for the order.
Cart line management
As a shopper changes their mind, the agent adjusts the cart. It reads the current selection and updates a line's quantity, keeping the cart accurate before checkout.
Read the cart via GET /selection, then adjust a line with PUT /lines/{line}/quantity/{quantity}.
Customer account flow
A storefront agent registers a new shopper or logs in a returning one before checkout. It registers or logs in the customer and reads the customer record, so the order is tied to the right account.
Register a shopper via POST /register or log one in with POST /login/{email}, then read the account with GET /customer.
86 endpoints — the centra checkout api powers a headless storefront checkout.
METHOD
PATH
DESCRIPTION
/selection
Read the current selection
/items/{item}
Add an item to the selection
/lines/{line}
Add a line to the selection
/lines/{line}/quantity/{quantity}
Set a line's quantity
/orders
Place an order
/payment
Submit a payment
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Centra Checkout API by hand means managing its API-Token header, and a bearer shared secret on some calls, against johnsmedley.centraqa.com and encoding the selection, order, and payment calls yourself. Through Jentic you install once, import it from the API Directory, store the credential once, and your agent calls it.
Permission scoping
Centra puts the item, line, and quantity in the URL path (/lines/{line}/quantity/{quantity}), so a rule can pin your agent to cart operations. You choose the operations it may call, so placing an order or submitting a payment is not included unless you add it.
Credential isolation
Your Centra API token and bearer secret are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'add an item to a cart' or 'place an order', and Jentic returns the matching operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Centra Checkout API through Jentic.
Is there a Centra Checkout API MCP server?
You don't need an MCP server to give your agent Centra. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the selection, order, and payment operations. That keeps your agent's context free of an extra server's tool definitions.
What authentication does the Centra Checkout API use?
It authenticates with an API token in the API-Token header, and some operations use a bearer shared secret, per its OpenAPI spec. Through Jentic these are stored encrypted by your own instance and injected at call time, so they never reach the agent's context.
Can I build a cart and place an order with the Centra Checkout API?
Yes. POST /items/{item} adds an item to the selection, GET /selection reads the current cart, and POST /orders followed by POST /payment places and pays for the order.
How do I add an item to a cart through Jentic?
Search Jentic for 'add an item to a cart', load the input schema, and execute POST /items/{item}. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Centra Checkout API?
Yes. Write a rule that allows only the selection-read and add-item operations, so the agent can build a cart and read it and nothing else, and every call it makes is logged. Placing an order or submitting a payment stays out unless you add those operations.
GET STARTED
Storefront reference data
Building a valid order needs reference data like markets and countries. The agent lists the markets and countries the store supports so a checkout workflow presents the right options.
List markets with GET /markets and countries with GET /countries to build a valid checkout.
/register
Register a customer
/login/{email}
Log in a customer
/customer
Read the customer
/markets
List markets
/selection
Read the current selection
/items/{item}
Add an item to the selection
/lines/{line}
Add a line to the selection
/lines/{line}/quantity/{quantity}
Set a line's quantity
/orders
Place an order
/payment
Submit a payment
/register
Register a customer
/login/{email}
Log in a customer
/customer
Read the customer
/markets
List markets
For Agents
Read a Centra selection, add items and lines, adjust line quantities, place an order with payment, register and log in customers, and list markets, countries, and warehouses.
Use for: Add a product to the cart, Change the quantity of a line in the cart, Read the current selection, Place an order and pay
Not supported: Does not manage catalog inventory, fulfill orders, or run store administration. Use for building a Centra selection and placing checkout orders only.
The Centra Checkout API powers a headless storefront checkout. It reads the current selection, adds items and lines to it, adjusts line quantities, and places an order with a payment. It also registers and logs in customers, reads the customer, and lists reference data such as markets, countries, and warehouses. Authentication uses an API token, with a bearer shared secret on some operations.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>