Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Open Data V1 Core 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%2Fdelijn.be%2Fdelijn" | 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%2Fdelijn.be%2Fdelijn" | 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 Open Data V1 Core API.
List the operating entities of the De Lijn network and the municipalities each serves
List and read municipalities, their stops, and the lines that run through them
Find the stops near a given set of coordinates
Look up a group of stops by their stop keys
Read the timetables for a group of stops
GET STARTED
Resolve lines and stops across the Flemish transit network
Patterns agents use Open Data V1 Core API for, with concrete tasks.
★ Agent-Driven Transit Lookups
An AI agent helps a traveller in Flanders by finding the stops nearest their location, then reading the lines and timetables for those stops. The agent passes a set of coordinates to the nearby-stops endpoint, selects the closest stops, and returns which lines serve them, so a travel assistant can answer 'how do I get there' from a plain-language request.
Find the stops near a given latitude and longitude, then return the lines that serve the closest stop
Network and Municipality Mapping
Build a map of the Flemish transit network by listing the operating entities, the municipalities each covers, and the stops and lines within them. This feeds a routing or coverage tool that needs the full structure of De Lijn services across a region.
List all municipalities for an entity, then enumerate the stops and lines in each
Stop Timetable Retrieval
Pull timetables for a chosen group of stops so a departures board or trip planner can show upcoming services. Given a set of stop keys, the API returns the schedules for those stops in one call.
Given a list of stop keys, retrieve the timetables for all of them and return the next departures
47 endpoints — the de lijn open data core api exposes the public transport network of flanders: its operating entities, the municipalities they serve, the stops, and the lines that run through them.
METHOD
PATH
DESCRIPTION
/entiteiten
List operating entities
/entiteiten/{entiteitnummer}/gemeenten
Municipalities served by an entity
/gemeenten
List municipalities
/gemeenten/{gemeenteNummer}/haltes
Stops in a municipality
/gemeenten/{gemeenteNummer}/lijnen
Lines through a municipality
/haltes
List stops
/haltes/indebuurt/{latlng}
Stops near coordinates
/haltes/lijst/{haltesleutels}/dienstregelingen
Timetables for a group of stops
/entiteiten
List operating entities
/entiteiten/{entiteitnummer}/gemeenten
Municipalities served by an entity
/gemeenten
List municipalities
/gemeenten/{gemeenteNummer}/haltes
Stops in a municipality
/gemeenten/{gemeenteNummer}/lijnen
Lines through a municipality
/haltes
List stops
/haltes/indebuurt/{latlng}
Stops near coordinates
/haltes/lijst/{haltesleutels}/dienstregelingen
Timetables for a group of stops
What agents get from Jentic-routed access to this vendor.
Setup
By hand you register for a subscription key, choose whether to send it in the header or the query, and learn the Dutch-language entity, municipality, stop, and line model before a lookup works. Through Jentic you connect once from the API Directory and your agent calls the operations by intent.
Permission scoping
Every operation is a read-only lookup over open transit data, so you choose exactly which your agent may call, such as stops and timetables while leaving out full network listings. The municipality and stop identifiers travel in the URL path, so a rule can bind the agent to specific path operations.
Credential isolation
Your subscription key is stored encrypted on your own Jentic One instance and injected into the request at execution time, never placed in the agent's prompt, logs, or context. You rotate it in one place.
Intent-based discovery
Agents search Jentic by intent such as 'stops near a location' or 'timetable for a stop', and Jentic returns the matching De Lijn operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Open Data V1 Core API through Jentic.
What authentication does the De Lijn Open Data API use?
The spec declares an apiKey subscription key: you send it either in the Ocp-Apim-Subscription-Key header or as a subscription-key query parameter. Through Jentic, your own Jentic One instance stores the key encrypted and attaches it to every request for you.
Can I find the stops nearest a location with the De Lijn API?
Yes. The nearby-stops endpoint takes a set of coordinates and returns the stops around that point, and you can then read the lines serving those stops and their timetables. You can also list stops by municipality or look them up by stop key.
What are the rate limits for the De Lijn Open Data API?
The OpenAPI spec does not state rate limits, and the subscription key is managed through De Lijn's API portal. Check the official documentation at https://data.delijn.be/ for current quotas before running heavy queries.
How do I query De Lijn transit data through Jentic?
Add the De Lijn Open Data API from the Jentic API Directory and connect your subscription key once. Your agent then searches by intent such as 'stops near a location' and calls the matching operation. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit which De Lijn lookups my agent is allowed to call?
Yes. Every operation is a read-only GET, so you grant your agent only the lookups it needs, such as stops and timetables while leaving out the full network listing. The municipality and stop identifiers sit in the URL path, so a rule can also pin the agent to specific path operations, and every call is logged.
Is there a De Lijn transit MCP server?
You don't need an MCP server to give your agent De Lijn data. Jentic connects it directly from the API Directory: import it, connect your key once, and your agent can look up stops, lines, and timetables without another server loading tool definitions into its context.
Know of an official OpenAPI document? Contribute it →
For Agents
Look up De Lijn's Flanders transit network: entities, municipalities, stops, and lines, find stops near coordinates, and read stop timetables. Reference data for the Flemish public transport system.
Use for: List all municipalities served by De Lijn, Find the nearest stops to a set of coordinates, Get the lines that pass through a municipality, I want the timetable for a specific stop
Not supported: Does not sell tickets, plan multi-modal routes, or cover transit outside Flanders. Use for looking up De Lijn stops, lines, and timetables only.
The De Lijn Open Data Core API exposes the public transport network of Flanders: its operating entities, the municipalities they serve, the stops, and the lines that run through them. You list and read entities, municipalities, stops, and lines, find the stops near a set of coordinates, and pull the timetables for a group of stops. It is a reference and lookup layer over the Flemish transit network, returning the structure an agent needs to plan around De Lijn services.
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>