Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the RoadGoat Cities 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%2Froadgoat.com%2Froadgoat-cities-api" | 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%2Froadgoat.com%2Froadgoat-cities-api" | 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 RoadGoat Cities API.
Search Destinations
Get Destination by ID
Auto-Complete Destinations
Query and filter RoadGoat Cities API records by parameters
Monitor RoadGoat Cities API operational status and events
GET STARTED
Patterns agents use RoadGoat Cities API for, with concrete tasks.
★ Media and Content Operations
Use the RoadGoat Cities API to perform media operations programmatically. The API provides 3 endpoints covering core functionality including search destinations, get destination by id, auto-complete destinations.
Call GET /destinations to search destinations
Automated Destinations Management
Automate destinations operations by combining multiple RoadGoat Cities API endpoints. Agents can get destination by id and then auto-complete destinations in a single workflow.
Call GET /destinations/{id} to get destination by id, then verify the result
AI Agent Integration via Jentic
AI agents discover and call RoadGoat Cities API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle basic tokens manually.
Search Jentic for 'search destinations', load the operation schema, and execute with Jentic-managed credentials
3 endpoints — the roadgoat cities api provides access to city and destination content including descriptions, photos, known-for tags, budget information, safety scores, and related destinations.
METHOD
PATH
DESCRIPTION
/destinations
Search Destinations
/destinations/{id}
Get Destination by ID
/destinations/auto_complete
Auto-Complete Destinations
/destinations
Search Destinations
/destinations/{id}
Get Destination by ID
/destinations/auto_complete
Auto-Complete Destinations
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the RoadGoat Cities API by hand means setting up HTTP Basic auth with your API key as the username and secret as the password, sending it on every call to the roadgoat.com v2 host, and handling each destinations lookup yourself. Through Jentic you install once, import the RoadGoat Cities API from the API Directory, store the credentials once, and your agent calls it.
Permission scoping
RoadGoat puts the destination id in the URL path (/destinations/{id}), so a rule can pin your agent to one destination and its lookups. You choose the operations it may call, and since this API is read-only the agent searches and reads destinations without any write path unless you add one.
Credential isolation
Your RoadGoat API key and secret are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'search destinations' or 'get a destination by id', and Jentic returns the matching RoadGoat Cities API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using RoadGoat Cities API through Jentic.
What authentication does the RoadGoat Cities API use?
The RoadGoat Cities API uses HTTP Basic authentication with username and password. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I search destinations with the RoadGoat Cities API?
Yes. Use the GET /destinations endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the RoadGoat Cities API?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I search destinations through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'search destinations'. Jentic returns the matching RoadGoat Cities API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the RoadGoat Cities API have?
The RoadGoat Cities API exposes 3 endpoints covering destinations operations.
Can I limit what my agent is allowed to do with the RoadGoat Cities API?
Yes. Jentic One is self-hosted by you, so your own rules decide which RoadGoat operations the agent may call and which credentials it may use. You can allow only the read operations you want, such as searching destinations with GET /destinations, looking one up with GET /destinations/{id}, or auto-completing with GET /destinations/auto_complete, and because this API is read-only there is no write path for the agent to take. Since the destination id sits in the URL path, a rule can also pin the agent to a single destination and its lookups.
For Agents
Programmatically search destinations, get destination by id. Covers 3 operations with basic authentication.
Use for: I need to destinations, I want to destination by id, Search for auto-complete destinations, List all records from RoadGoat Cities API
Not supported: Does not handle payments, communications, or crm - use for media and content only.
The RoadGoat Cities API provides access to city and destination content including descriptions, photos, known-for tags, budget information, safety scores, and related destinations. It follows the JSON:API specification and provides rich data about cities worldwide for travel applications. The API exposes 3 endpoints secured with basic authentication.
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>