Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the QuizBase 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%2Frunriva.com%2Frunriva" | 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%2Frunriva.com%2Frunriva" | 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 QuizBase API.
Draw a random sample of up to 50 trivia questions filtered by difficulty, type, category, or topic
Browse the question bank with cursor pagination and delta-sync changes using updated_since
Fetch up to 250 exact questions in one call by ids and map them to another language with content_language
Filter questions by license, such as CC-BY-4.0 or MIT, and by source dataset to control reuse terms
GET STARTED
Target questions by cultural region codes and curated topics with their facets
Report a wrong translation, factual error, or attribution problem on a question
Check the API key's details and a 30-day usage series
Patterns agents use QuizBase API for, with concrete tasks.
★ Quiz-generating agent through Jentic
A developer building a quiz bot wants questions on demand without running a database. Through Jentic the agent searches for 'get random trivia questions', receives the QuizBase operation with its input schema, and calls GET /api/v1/questions/random with amount, difficulty, type, and topic. Each question comes back with its license and source, so the bot can attribute it when it posts the quiz.
Call GET /api/v1/questions/random with amount 10, difficulty 'hard', and type 'multiple', then format the questions as a quiz and list each question's license and source
Licence-aware content for commercial apps
Apps that ship trivia commercially need to know what they may reuse. QuizBase returns a per-record license on every question, and GET /api/v1/questions and GET /api/v1/questions/random accept a license filter with values such as CC-BY-4.0, CC-BY-SA-4.0, and MIT, plus source and exclude_source filters to drop datasets a team does not want.
Call GET /api/v1/questions with license 'MIT', difficulty 'medium', and limit 50, and return the questions with their author and source fields
Multilingual quiz sets
A quiz app that runs in English and Polish wants the same set of questions in both languages. GET /api/v1/questions takes ids, a comma-separated list of up to 250 UUIDs, and content_language to return the sibling record in the target language for each id. Ids that cannot be resolved are reported in meta.missing rather than dropped.
Call GET /api/v1/questions with ids set to the 20 question UUIDs from an English quiz and content_language 'pl', then report any ids listed in meta.missing
Local question cache with delta sync
Some apps keep a local copy of the question bank for offline play. GET /api/v1/questions pages through records with cursor and limit, and the updated_since filter returns only records changed since the last sync. GET /api/v1/stats and GET /api/v1/categories give totals and the category list to check coverage.
Call GET /api/v1/questions with updated_since set to the last sync timestamp and follow the cursor until no pages remain, then store the changed questions
14 endpoints — the quizbase api serves multilingual trivia questions blended and deduplicated from open datasets, with english and polish available at launch.
METHOD
PATH
DESCRIPTION
/api/v1/questions/random
Random questions sample
/api/v1/questions
Browse questions with filters
/api/v1/questions/{id}
Single question by id
/api/v1/topics
List curated topics
/api/v1/categories
List categories
/api/v1/report
Report a problem with a question
/api/v1/usage
30-day usage series
/api/v1/questions/random
Random questions sample
/api/v1/questions
Browse questions with filters
/api/v1/questions/{id}
Single question by id
/api/v1/topics
List curated topics
/api/v1/categories
List categories
/api/v1/report
Report a problem with a question
/api/v1/usage
30-day usage series
What agents get from Jentic-routed access to this vendor.
Setup
Wiring QuizBase by hand means choosing between the X-API-Key header and a bearer token, keeping publishable and secret keys apart, and handling cursor pagination and the ids batch mode. Through Jentic you install once, import QuizBase from the API Directory, store the key once, and your agent calls it.
Permission scoping
QuizBase carries its filters in query parameters, so rules bound which operations your agent may call rather than which questions it sees. You choose the operations it may call, so account reads like key details and usage, or filing reports, are not included unless you add them.
Credential isolation
Your QuizBase 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 'get random trivia questions' or 'list quiz topics', and Jentic returns the matching QuizBase operation with its input schema so the agent calls the right endpoint without reading the docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using QuizBase API through Jentic.
What authentication does the QuizBase API use?
The QuizBase API declares two schemes in its OpenAPI spec that carry the same key: ApiKey, sent in the `X-API-Key` header, and BearerKey, sent as `Authorization: Bearer`. Keys come in publishable (qb_pk_) and secret (qb_sk_) forms. POST /api/v1/report declares no security requirement, so problem reports need no key. Through Jentic the key is held by your own Jentic One instance and attached at call time.
Can I filter QuizBase questions by license?
Yes. GET /api/v1/questions and GET /api/v1/questions/random accept a license parameter with values including CC-BY-SA-4.0, CC-BY-SA-3.0, CC-BY-4.0, MIT, and proprietary. Every question also returns its own license, author, and source, so you can attribute each record.
What are the rate limits for the QuizBase API?
The OpenAPI spec does not specify rate limits. GET /api/v1/usage returns a 30-day usage series for your key and GET /api/v1/me returns the key's details; check the QuizBase site at https://quizbase.runriva.com for plan limits.
How do I get random trivia questions through Jentic?
Search Jentic for 'get random trivia questions', load the GET /api/v1/questions/random operation, and execute it with amount (up to 50) plus filters such as difficulty, type, topic, and lang. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a QuizBase MCP server?
You don't need an MCP server to give your agent QuizBase. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent finds the question and topic operations it needs on demand, without loading extra tool definitions into its context.
Can I limit what my agent is allowed to do with the QuizBase API?
Yes. For a quiz bot, write a rule that allows only GET /api/v1/questions/random and GET /api/v1/topics. The agent can draw questions and pick topics but cannot read your key details or usage, or file reports, and each call it makes is logged.
For Agents
Pull random or filtered trivia questions by category, difficulty, type, topic, region, and license, fetch exact questions by id, and map a set into another language.
Use for: Get 10 random hard multiple-choice trivia questions about history, I need a quiz of 20 easy true or false questions in Polish, Find all trivia questions under the MIT license, List all curated quiz topics
Not supported: Does not host quizzes, score players, or run a learning management system. Use for sourcing licensed trivia questions only.
The QuizBase API serves multilingual trivia questions blended and deduplicated from open datasets, with English and Polish available at launch. Every question carries its own license, author, and source, and keeps a stable UUID v7 id, so apps can attribute content and avoid repeats. Questions can be sampled at random or browsed with cursor pagination and filtered by category, difficulty, question type, topic, tags, cultural region, source dataset, and license, with an updated_since filter for delta sync.
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>