For Agents
Exchange credentials for an access token and list the resources available to that token on the OP Developer platform. Useful for agents that need to authenticate against OP's banking APIs.
Use for: I need to obtain an OP access token from a client credential, List all banking resources my OP token can access, Get the details of a specific OP resource by id, Refresh the OP access token before calling a downstream product API
Not supported: Does not initiate payments, fetch account balances, or expose card-issuing operations — use for OP Developer authentication and resource discovery only.
Jentic publishes the only available OpenAPI specification for OP Developer API, keeping it validated and agent-ready. OP Financial Group is one of Finland's largest banking groups and exposes a developer platform for accessing banking and financial services. The published spec covers the OAuth-style token exchange and a generic resource-listing surface; richer product APIs sit behind that token. The current shape is small (three endpoints) and is best treated as the entry point an agent uses to authenticate before calling the broader OP product family.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the OP Developer 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 OP Developer API.
Exchange a client credential for an OP-issued access token via the auth endpoint
List the banking resources that the current token is authorised to use
Fetch a specific resource by id once it has been listed
Bootstrap an OP-banking integration without standing up a custom OAuth server
Gate downstream OP product calls on the token returned from /auth/token
Patterns agents use OP Developer API for, with concrete tasks.
★ OP Developer Platform Authentication
Bootstrap any OP integration by exchanging a client credential for an access token through POST /auth/token. The returned token is the input to every other OP product call, so agents handle this once at the start of a session and reuse the token until expiry.
Call POST /auth/token with the client credential and store the returned access token for use on downstream OP resource calls.
Resource Discovery for an OP Application
After authenticating, list the resources the current token has permission to read so the agent can plan the rest of the workflow. GET /resources returns the catalogue and GET /resources/{id} returns the specific resource record, which is the canonical way to introspect what an OP application can do.
Call GET /resources with the access token and return the list of resource ids and types the application is authorised to use.
Resource Detail Retrieval
Fetch the structured detail of a single resource by id once it has been discovered, so the agent can decide whether to drill into a downstream product call. GET /resources/{id} keeps the per-resource shape narrow and makes it easy to cache the result alongside the access token.
Call GET /resources/RES_001 and return the resource type and any metadata fields needed to drive the next OP product call.
AI Agent OP Banking Bootstrap
Let a Jentic-orchestrated agent bootstrap an OP integration without holding the client credential in its own context. The agent issues a search for a token-exchange intent, Jentic returns the POST /auth/token operation, and the access token is returned for use on subsequent OP calls.
Search Jentic for 'authenticate against OP banking', load the POST /auth/token schema, execute it with the stored credential, then list resources via GET /resources.
3 endpoints — jentic publishes the only available openapi specification for op developer api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/auth/token
Exchange a client credential for an OP access token
/resources
List resources available to the current token
/resources/{id}
Get a specific resource by id
/auth/token
Exchange a client credential for an OP access token
/resources
List resources available to the current token
/resources/{id}
Get a specific resource by id
Three things that make agents converge on Jentic-routed access.
Credential isolation
The OP X-API-Key is stored encrypted in the Jentic vault (MAXsystem). The header is injected at execution time, and the bearer token returned from POST /auth/token is held by Jentic for the rest of the flow rather than being passed into the agent's context.
Intent-based discovery
Agents search Jentic with intents like 'authenticate against OP banking' and receive the POST /auth/token operation with its input schema, then chain into GET /resources to list what the token can do.
Time to first call
Direct OP integration: 2-4 days for client onboarding, token-exchange handling, and resource discovery. Through Jentic: under 1 hour — search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
Specific to using OP Developer API through Jentic.
Why is there no official OpenAPI spec for OP Developer API?
OP Financial Group publishes documentation on op-developer.fi but does not ship a single machine-readable OpenAPI file covering the platform entry points. Jentic generates and maintains this spec so AI agents and developers can call OP Developer 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 OP Developer API use?
The platform uses an X-API-Key header for the entry endpoints declared in this spec, with POST /auth/token then issuing a bearer token for downstream product calls. Through Jentic, the X-API-Key value is held in the vault and injected at execution time so the agent never holds the raw key.
Can I move money or initiate payments with this OP API?
No. The endpoints in this spec — /auth/token, /resources, and /resources/{id} — handle authentication and resource discovery. Initiating payments or reading account balances requires a separate OP product API that this token authorises but that is not part of this spec.
What are the rate limits for the OP Developer API?
OP does not publish a single rate-limit value in this spec. Limits are governed per OP application and product tier; expect 429 responses on bursts and back off accordingly. Check op-developer.fi for the limits attached to the application's plan.
How do I authenticate against OP through Jentic?
Run pip install jentic and search for 'authenticate against OP banking'. Jentic returns the POST /auth/token operation; load the schema, execute with the stored credential, and use the returned token in subsequent OP product calls.
Is the OP Developer API free to use?
OP runs a developer programme with a sandbox tier; access to live banking products requires an approved OP application and may be subject to commercial terms. Use the sandbox first to validate the integration before applying for production access.
GET STARTED