Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the FlightQueue 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%2Fflightqueue.com%2Fflightqueue" | 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%2Fflightqueue.com%2Fflightqueue" | 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 FlightQueue API.
Get current security, check-in, and immigration wait estimates for an airport
Read hourly wait-time predictions for an airport
Check FAA delay status for an airport
Pull historical wait-time patterns for an airport
List the supported airports
GET STARTED
Create or update a wait-time alert
Fetch bulk wait times across many airports at once
Patterns agents use FlightQueue API for, with concrete tasks.
★ Agent departure timing
An AI agent connected through Jentic advises a traveller when to leave for the airport by reading the current security, check-in, and immigration wait estimates and the hourly predictions for their departure airport, so the answer reflects live conditions rather than a fixed buffer, without the developer wiring the auth or paging logic.
Read the current and predicted security wait times for a departure airport and recommend a leave-by time
Delay-aware alerting
A travel assistant creates a wait-time alert for a traveller's airport and checks FAA delay status so it can warn them the moment conditions worsen, turning the alert endpoint and the delay endpoint into a watch on a single airport.
Create a wait-time alert for an airport and check its FAA delay status to warn the traveller of worsening conditions
Operations dashboard
An operations tool pulls bulk wait times across a set of hub airports in one call and reads each one's historical patterns, so a team can see where queues are building and compare the day against the airport's norm.
Fetch bulk wait times for a set of hub airports and compare each against its historical pattern
7 endpoints — the flightqueue api reports real-time airport intelligence for more than 8,000 airports, covering current security, check-in, and immigration wait estimates.
METHOD
PATH
DESCRIPTION
/airports
List supported airports
/airports/{iata}/wait-times
Current security, check-in, and immigration wait estimates
/airports/{iata}/predictions
Hourly wait-time predictions
/airports/{iata}/delays
FAA delay status for an airport
/airports/{iata}/historical
Historical wait-time patterns
/alerts
Create or update a wait-time alert
/airports/bulk
Bulk wait times across many airports
/airports
List supported airports
/airports/{iata}/wait-times
Current security, check-in, and immigration wait estimates
/airports/{iata}/predictions
Hourly wait-time predictions
/airports/{iata}/delays
FAA delay status for an airport
/airports/{iata}/historical
Historical wait-time patterns
/alerts
Create or update a wait-time alert
/airports/bulk
Bulk wait times across many airports
What agents get from Jentic-routed access to this vendor.
Setup
Wiring FlightQueue by hand means handling its bearer or API-key auth, keeping the agent key and developer key straight, and paging the per-airport wait, prediction, delay, and historical endpoints yourself. Through Jentic you install once, import FlightQueue from the API Directory, store the key once, and your agent calls it.
Permission scoping
FlightQueue puts the IATA airport code in the URL path (/airports/{iata}/...), so a rule can pin your agent to read-only wait-time and delay lookups for airports. You choose the operations it may call, so write operations like creating an alert or the bulk Enterprise lookup are not included unless you add them.
Credential isolation
Your FlightQueue key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get airport security wait times' or 'check an airport's FAA delay', and Jentic returns the matching FlightQueue 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 FlightQueue API through Jentic.
What authentication does the FlightQueue API use?
The FlightQueue API accepts either a bearer token or an API key in the `X-API-Key` header, per its OpenAPI spec. The same keys work in both forms, and they come as an agent key or a developer key. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never lands in the agent's context.
Is there a FlightQueue MCP server?
You don't need an MCP server to give your agent FlightQueue. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the wait-time, prediction, and delay operations on demand, without a separate server's tool definitions loaded into its context.
Can I limit what my agent is allowed to do with the FlightQueue API?
Yes. Write a rule that allows only the read operations, such as current wait times, predictions, and delay status, so the agent can advise on timing but cannot create alerts or run bulk Enterprise lookups, and every call it makes is logged.
Can I get predicted wait times with the FlightQueue API?
Yes. The predictions endpoint returns hourly wait-time predictions for an airport by its IATA code, and the historical endpoint returns the airport's past wait patterns so an agent can compare the forecast against the norm.
What are the rate limits for the FlightQueue API?
The OpenAPI spec does not specify rate limits, and the bulk wait-times call is noted as an Enterprise feature. Check the vendor documentation at https://flightqueue.com/pricing for current plan limits.
How do I check an airport's wait time through Jentic?
Search Jentic for 'get airport security wait times', which returns the FlightQueue wait-times operation with its input schema, then pass the airport's IATA code and read the current estimate back. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Read real-time airport intelligence: current security, check-in, and immigration wait times, hourly predictions, FAA delay status, and historical patterns for a given airport, plus wait-time alerts.
Use for: Get the current security wait time at an airport, Check predicted wait times for the next few hours, Find out whether an airport has an FAA delay, Look up historical wait patterns for an airport
Not supported: Does not handle flight booking, gate assignments, or baggage tracking. Use for airport wait times, delays, and predictions only.
The FlightQueue API reports real-time airport intelligence for more than 8,000 airports, covering current security, check-in, and immigration wait estimates. It returns hourly wait-time predictions, FAA delay status, and historical wait patterns for a given airport, so an agent can judge when to leave for a flight. It lists the airports it supports, offers a bulk wait-times call for many airports at once, and lets a caller create or update an alert that fires when a wait time crosses a threshold.
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>