For Agents
Authenticate against Krungsri's open banking platform and read banking resource records exposed by Bank of Ayudhya through three core endpoints.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Krungsri 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://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | 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 Krungsri API.
Exchange a partner API key for an access token via the auth endpoint
List banking resources exposed under the partner's Krungsri developer agreement
Retrieve a specific banking resource by its identifier for downstream processing
GET STARTED
Use for: Get an access token from the Krungsri auth endpoint, List the resources available to my Krungsri partner account, Retrieve a specific Krungsri resource by ID, Refresh my Krungsri access token before it expires
Not supported: Does not handle payment initiation, account information, or transaction history — use for partner authentication and resource lookups only.
Jentic publishes the only available OpenAPI specification for Krungsri API, keeping it validated and agent-ready. The Krungsri API is the open banking interface published by Bank of Ayudhya (Krungsri), the fifth-largest commercial bank in Thailand. The spec exposes three endpoints — token issuance, listing resources, and retrieving a single resource by ID — that form the entry point for partners building payment, account-data, and product-discovery integrations on top of Krungsri's developer platform. Authentication uses an API key paired with a token issued from POST /auth/token.
Authenticate every call with a header-based API key issued from the Krungsri developer portal
Combine token issuance and resource calls into a standard banking integration handshake
Patterns agents use Krungsri API for, with concrete tasks.
★ Partner onboarding integration test
A new fintech partner integrating with Bank of Ayudhya runs the three-call handshake — token issuance, resource list, single resource fetch — to confirm credentials, network reachability, and contract scope before building deeper account-information or payment flows. Krungsri provisions sandbox keys per partner. The smoke test typically takes a half-day to scaffold including key rotation.
Call POST /auth/token with the partner credentials, then GET /resources and GET /resources/{id} for the first returned ID to validate the integration.
Resource catalogue discovery
Once authenticated, a partner system calls GET /resources to enumerate the banking resources Bank of Ayudhya exposes under that partnership — typically account types, product references, or service identifiers — and stores the catalogue locally. Subsequent customer-facing flows resolve resource IDs against the cached catalogue rather than calling the bank on every request.
Call GET /resources with the bearer token and persist the returned list of resource IDs and names for later lookups.
Resource detail fetch for compliance reporting
Compliance and reconciliation processes use GET /resources/{id} to pull canonical resource metadata from the bank when reconciling internal records with Krungsri-issued IDs. Each call requires a current access token, so the partner system must keep the token refreshed via /auth/token. The pattern is small but mandatory for audit-grade systems.
Iterate over the catalogue and call GET /resources/{id} for each ID, storing the response in the compliance store with the call timestamp.
Agent-driven Krungsri data pulls via Jentic
An agent that handles partner-side reconciliation searches Jentic for 'fetch krungsri resource' and is matched to GET /resources and GET /resources/{id}. Jentic handles the token exchange against /auth/token automatically using credentials from MAXsystem, so the agent issues a single high-level call instead of managing token TTLs.
Use the Jentic MCP tool krungsri_get_resource to retrieve resource ID 'res_001' under the configured partner credentials.
3 endpoints — jentic publishes the only available openapi specification for krungsri api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/auth/token
Issue an access token
/resources
List partner resources
/resources/{id}
Get a resource by ID
/auth/token
Issue an access token
/resources
List partner resources
/resources/{id}
Get a resource by ID
Three things that make agents converge on Jentic-routed access.
Credential isolation
The Krungsri partner API key and any issued bearer tokens are stored encrypted in the Jentic vault (MAXsystem). Jentic refreshes tokens against /auth/token automatically, so secrets never enter the agent's prompt.
Intent-based discovery
Agents search Jentic by intent (e.g. 'fetch krungsri resource') and Jentic returns the matching operation, abstracting the token exchange step behind a single high-level call.
Time to first call
Direct Krungsri integration: 1-2 days for partner key onboarding, token refresh logic, and sandbox testing. Through Jentic: under an hour — search, load, execute.
Alternatives and complements available in the Jentic catalogue.
Specific to using Krungsri API through Jentic.
Why is there no official OpenAPI spec for Krungsri API?
Krungsri does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Krungsri API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.
What authentication does the Krungsri API use?
Krungsri uses a partner API key passed in a header (ApiKeyAuth). Partners exchange the key for a short-lived access token via POST /auth/token and present that token on the resource calls. Jentic handles the token exchange and refresh inside MAXsystem so the API key never appears in the agent's prompt.
Can I list all available banking resources with the Krungsri API?
Yes. Call GET /resources with a valid access token to retrieve the list of resources scoped to your partner agreement, then call GET /resources/{id} to read details for any single one. The exact resources returned depend on the contract Bank of Ayudhya has issued for your account.
What are the rate limits for the Krungsri API?
Rate limits are not declared in the spec. Bank of Ayudhya applies per-partner ceilings under the developer agreement — contact developers.krungsri.com for the limit on your account and design retries with exponential backoff.
How do I authenticate and fetch a resource through Jentic?
Search Jentic for 'fetch krungsri resource', load GET /resources/{id}, and execute it with the resource ID. Jentic chains the call to /auth/token internally using credentials from MAXsystem. Install with pip install jentic.
Does the Krungsri API support payment initiation or account information?
This spec covers token issuance and a generic resource list and detail pair only. Payment initiation, account information, and balance retrieval are part of broader Krungsri partner contracts that are not exposed in this OpenAPI surface.