Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Creditas PSD2 Accounts 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%2Fcreditas.cz%2Fcreditas" | 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%2Fcreditas.cz%2Fcreditas" | 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 Creditas PSD2 Accounts API.
List a client's payment accounts under AISP consent
Read the current balance of a specific account
Retrieve an account's transaction history
Operate within PSD2 account-information scopes
Patterns agents use Creditas PSD2 Accounts API for, with concrete tasks.
★ Account aggregation
Personal-finance and treasury tools aggregate balances across banks. The Creditas PSD2 API lists a client's payment accounts and returns each balance under AISP consent, so an aggregator can show a current position for Creditas holdings.
List the client's Creditas accounts and read each account's current balance
Transaction reconciliation
Bookkeeping systems reconcile ledger entries against bank transactions. The API returns an account's transaction history so a reconciliation job can match entries and flag discrepancies.
Retrieve the transaction history for an account and match it against ledger entries
Agent-driven balance check
A finance assistant can answer balance questions under consent. Through Jentic, an agent uses the PSD2 token and certificate to list accounts and read balances in response to a user request.
Under AISP consent, list a client's accounts and summarize their balances for the user
3 endpoints — the creditas psd2 accounts api is a european open-banking (aisp) interface from the czech bank creditas.
METHOD
PATH
DESCRIPTION
/v1/my/accounts
List a client's payment accounts
/v1/my/accounts/{accountId}/balance
Get an account balance
/v1/my/accounts/{accountId}/transactions
Get account transactions
/v1/my/accounts
List a client's payment accounts
/v1/my/accounts/{accountId}/balance
Get an account balance
/v1/my/accounts/{accountId}/transactions
What agents get from Jentic-routed access to this vendor.
Setup
Creditas needs an OAuth2 authorization-code token and a mutual TLS client certificate before any read. With Jentic One you install once, import the three operations from the API Directory, and both credential layers are wired in one place.
Permission scoping
Accounts are addressed by an account id in the path, so you can scope an agent to specific accounts and to read-only balance and transaction operations.
Credential isolation
Your OAuth2 secret and the client certificate are stored encrypted by your own Jentic One instance and used only at execution time, so they never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents find the right account operation through Jentic's intent search, matching a request like showing an account's transactions to the matching Creditas endpoint.
Alternatives and complements available in the Jentic catalogue.
Specific to using Creditas PSD2 Accounts API through Jentic.
How does the Creditas PSD2 API authenticate?
It uses two layers: an OAuth2 authorization-code token carrying AISP account scopes, plus a mutual TLS (mutualTLS) client certificate for the connection. Jentic One manages both and injects them at execution time.
Can I limit what my agent can do with the Creditas API?
Yes. Because each account is addressed by an account id in the path, you can scope an agent to read-only operations and even to specific accounts, keeping balances and transactions separate from any write access elsewhere.
What is AISP access under PSD2?
AISP is the account-information service role under PSD2: with the customer's consent it grants read access to accounts, balances, and transactions, but not the ability to move money.
Can this API initiate payments?
No. These endpoints are account-information only; payment initiation under the PISP role is out of scope for this interface.
Why does Creditas require a client certificate?
PSD2 mandates mutual TLS between the bank and a licensed third party, so a client certificate authenticates the connection in addition to the OAuth2 token.
GET STARTED
Get account transactions
Know of an official OpenAPI document? Contribute it →
For Agents
Lets an AI agent read a Creditas client's payment accounts, balances, and transactions under PSD2 AISP consent.
Use for: I need to list a customer's Creditas accounts, What is the balance on this account?, Pull the recent transactions for an account, Access account data under PSD2 consent
Not supported: Does not initiate payments, open accounts, or issue cards: use it to read Creditas accounts, balances, and transactions under PSD2 AISP only.
The Creditas PSD2 Accounts API is a European open-banking (AISP) interface from the Czech bank Creditas. Under PSD2 account-information scopes, an authorized integration can list a client's payment accounts, read the balance of a specific account, and retrieve the transaction history for an account. Access requires an OAuth2 authorization-code token and a mutual TLS (mutualTLS) client certificate.
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>