Flight MCP API
55
AI ReadinessFoundational (C)55/100
Official vendor OpenAPI document · agent-readyData EnrichmentData TransformationapiKey, bearer3 EndpointsREST
For Agents
Search normalized flight offers over REST, or query already-cached offers without an account, and confirm service health before searching.
Use for: Search for flight offers between two airports, Find normalized flight offers for a given date, Query cached flight results without signing up, Get flight offers in a single consistent shape
Not supported: Does not handle booking, payment, or seat selection. Use for searching normalized flight offers only.
The Flight offer search API searches flight offers over REST and returns them in one normalized shape, so an agent reads a consistent result regardless of the underlying source. It offers a standard search for live offers and a separate cached search that answers from recent results without an account, and cache hits do not consume monthly plan calls. A lightweight health check lets a caller confirm the service is up before issuing a search.
Install Jentic One Beta
Connect the Flight MCP API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Flight MCP 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.
1
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%2Fflight-mcp.com%2Fflight-mcp" | sh2
Step 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%2Fflight-mcp.com%2Fflight-mcp" | 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.
Capabilities
What an agent can do with Flight MCP API.
Search live flight offers and get them back in one normalized shape
Query already-cached flight offers without an account
Reuse cached results so repeat searches do not spend monthly plan calls
Check service health before issuing a search
Use Cases
Patterns agents use Flight MCP API for, with concrete tasks.
★ Agent flight search
An AI agent connected through Jentic answers a travel question by calling the flight search endpoint and reading back offers in one normalized shape, so it can compare options without the developer reconciling different providers' result formats by hand.
Search flight offers for a route and date and return the normalized list to the model to compare
Cost-aware repeat lookups
A monitoring tool checks fares repeatedly by using the cached search, which answers from recent results without an account and does not consume monthly plan calls on a cache hit, so frequent polling stays cheap.
Poll the cached search endpoint for a route to detect a fare change without spending plan calls
Normalized provider comparison
A trip-planning assistant leans on the single normalized shape of each offer to line up itineraries side by side, checking service health first so a search is only issued when the backend is available.
Confirm the service is healthy, then search offers for two routes and present them in one comparable shape
Key Endpoints
3 endpoints — the flight offer search api searches flight offers over rest and returns them in one normalized shape, so an agent reads a consistent result regardless of the underlying source.
METHOD
PATH
DESCRIPTION
POST
/v1/flights/search
Search normalized flight offers
POST
/v1/flights/search/cached
Search already-cached flight offers without an account
GET
/healthz
Check service health
POST
/v1/flights/search
Search normalized flight offers
POST
/v1/flights/search/cached
Search already-cached flight offers without an account
GET
/healthz
Check service health
Jentic AI Readiness Score
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.
F
Flight MCP API
- Foundational (C)55/100
93
Foundational Compliance65
Developer Experience & Jentic Compatibility31
AI-Readiness & Agent Experience94
Agent Usability55
Security67
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
93
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 4
99%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
75%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
65
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: BSignals: 4
1%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
58%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
31
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: FSignals: 4
14%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
67%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
43%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
55
Security
Trust, risk posture, and security compliance.
Grade: CSignals: 1
55%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
67
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: BSignals: 1
67%
Descriptive Richness
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>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring this flight-search API by hand means handling its bearer or API-key auth, choosing between the live search and the account-free cached search, and parsing the normalized offer shape yourself. Through Jentic you install once, import it from the API Directory, store the key once, and your agent calls it.
Permission scoping
The flight-search API carries the route and dates in the request body, so rules bound which operations your agent may call, not which route. Limit it to the search operations it needs, and the account-free cached search and the health check stay available without any credential at all.
Credential isolation
Your flight-search API 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 'search flight offers' or 'find cached flight results', and Jentic returns the matching flight-search operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Flight MCP API through Jentic.
What authentication does the Flight MCP API use?
The flight search endpoint accepts either a bearer token or an API key in the `x-api-key` header, per its OpenAPI spec. The health check and the cached-search endpoint need no credential. 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 Flight MCP server?
Jentic connects the Flight MCP API directly from the API Directory, so you don't set up a separate server to use it: import it, store your credential once, and your agent calls the search and cached-search operations on demand, without extra tool definitions loaded into its context.
Can I limit what my agent is allowed to do with the Flight MCP API?
Yes. The search parameters travel in the request body, so a rule bounds which operations the agent may call rather than which route. Allow only the search operations, and the agent can look up flight offers but reaches nothing else, with every call logged.
Can I search flights without an account using the Flight MCP API?
Yes. The cached-search endpoint answers from recent results and needs no credential, and because it serves cache hits it does not consume monthly plan calls, which makes it suited to frequent polling.
What are the rate limits for the Flight MCP API?
The OpenAPI spec does not state a numeric rate limit, though cache hits on the cached-search endpoint do not count against monthly plan calls. Check the vendor documentation at https://flight-mcp.com for current plan limits.
How do I search flights through Jentic?
Search Jentic for 'search flight offers', which returns the Flight MCP search operation with its input schema, then issue the route and date and read the normalized offers back. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED