# QuizBase MCP server

MCP server for trivia: 1.4M+ questions (EN+PL), 24 categories + 4 prompts, OAuth 2.1.

## Links
- Registry page: https://www.getdrio.com/mcp/com-runriva-quizbase-mcp
- Website: https://quizbase.runriva.com/docs/sdks/mcp-server

## Install
- Endpoint: https://quizbase.runriva.com/mcp
- Auth: Auth required by registry metadata

## Setup notes
- Remote header: Authorization (required; secret)
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://quizbase.runriva.com/mcp
- Header: Authorization

## Tools
- quizbase_random (Get random trivia questions) - Fetch N random trivia questions matching filters. Quality-first: by default excludes questions flagged for review (use quality='all' to include for audit/research).

USE WHEN: building a quiz, sampling content for warmup, generating practice sets. NOT WHEN: you need a specific question ID (use quizbase_question_by_id) or want to explore a topic deeply with facets (use quizbase_topic_by_slug).

KEY FILTERS:
- amount: 1-50, default 10.
- lang: ISO 639-1. Default "en". Supported: en, pl. Strict — unknown language returns 400.
- category (slug): e.g. geography, history, science-and-nature. Full list via quizbase_categories.
- difficulty: trivial | easy | medium | hard | expert. LLM-calibrated. Records not yet LLM-rated hold the importer placeholder (mostly "medium" for factoid sources).
- type: multiple | boolean (default both; no text_input in random).
- regions (cultural affinity, AND): empty in data = no cultural advantage assumed. Lowercase ISO 3166-1 alpha-2 ('us', 'pl', 'gb') + cultural codes ('jewish', 'christian-catholic', 'islam'). Filter for content statistically more likely known by residents/members. Discover via quizbase_regions.
- source (array): include only these source databases (one or more of 12: opentdb, opentriviaqa, kqa-pro, entityq, mintaka, mkqa, nq-open, creak, qasc, arc, webq, quizbase).
- exclude_source (array): drop these sources, e.g. ["entityq"] for human-curated only. Applied after source.
- license (SPDX): CC-BY-SA-4.0 | CC-BY-SA-3.0 | MIT | etc. Restrict to redistribution-friendly content.
- topic (curated slug): higher precision than tags. Alias resolver matches subcategories+tags. List via quizbase_topics.
- topics_any: OR over curated topics, max 10.
- tags (AND), tags_any (OR), subcategory: raw taxonomy. Use topic if available.
- quality: 'high' (default, recommended) = cleanest, most broadly-useful. 'standard' = broader pool incl. niche/too-specific (more volume). 'all' = audit/research, includes flagged — when 'all', each question gains a "quality" field ('high' or 'needs_review').
- exclude (UUIDs, max 250): de-dupe within a quiz session.

OUTPUT: { questions: [...], meta: { count, language } }. Each question carries full per-record attribution (source, author, license, licenseVersion, licenseUrl, sourceId, url, modifications, lastModified) — identical shape to REST /api/v1/questions/random.

ATTRIBUTION REQUIRED if you redistribute. CC-BY-SA modifications must be credited per § 3(a)(1)(B) using each question's own attribution object.

COMMON MISTAKES: forcing lang='pl' for a global audience (use 'en' default); skipping quality (default already excludes flagged content — only pass quality='all' for audit); using tags when a curated topic exists (worse precision). Endpoint: https://quizbase.runriva.com/mcp
- quizbase_list (Browse questions catalog with cursor pagination) - Cursor-paginated browse over the catalog. Quality-first: by default excludes questions flagged for review (use quality='all' for full pool).

USE WHEN: full catalog sync, delta sync (updated_since), exhaustive enumeration by filter. NOT WHEN: you only need N random samples (use quizbase_random) or a single record (use quizbase_question_by_id).

PAGINATION: stable cursor over id UUIDv7 DESC. First call: omit cursor. Next: pass meta.nextCursor. Stop when nextCursor is null.

KEY FILTERS (full parity with REST):
- lang: ISO 639-1, default "en". Supported: en, pl.
- category (slug), difficulty (trivial|easy|medium|hard|expert — LLM-calibrated), type (multiple|boolean), subcategory (raw slug).
- tags (AND), tags_any (OR, max 10): raw tag slugs.
- topic (curated, alias resolver), topics_any (OR over curated): higher precision than tags.
- regions (cultural affinity, AND): empty = no cultural advantage assumed. Lowercase ISO 3166-1 alpha-2 ('us', 'pl', 'gb') + cultural codes ('jewish', 'christian-catholic', 'islam'). Filter for content statistically more likely known by residents/members. Discover via quizbase_regions.
- source (array): include only these of 12 (opentdb, opentriviaqa, kqa-pro, entityq, mintaka, mkqa, nq-open, creak, qasc, arc, webq, quizbase).
- exclude_source (array): drop these sources, e.g. ["entityq"]. Applied after source.
- license (SPDX): e.g. CC-BY-SA-4.0, MIT.
- quality: 'high' (default) = cleanest, most broadly-useful. 'standard' = broader pool incl. niche/too-specific. 'all' = full pool incl. flagged; when 'all', each question gains a "quality" field ('high' or 'needs_review').
- updated_since (ISO 8601): only questions updated after this — for delta sync caches.

BATCH + TRANSLATION MAPPING:
- ids (up to 250): fetch those exact records in one call (anti-repeat, deep-links, restoring a saved set). Terminal selector — browse filters and cursor are ignored. Missing ids → meta.missing.
- content_language (en|pl): with ids, returns each question's sibling in that CONTENT language across the translation chain — the same questions in another language. Distinct from lang (labels only).

PAGINATION + COUNTING:
- cursor (string): from previous meta.nextCursor. Omit for page 1.
- limit (1-100, default 20).
- count: none (default, skip — page via nextCursor) | exact (precise COUNT(*), index-only ~25-90ms).

OUTPUT: { questions: [...], meta: { count, countMode, language, nextCursor, total? } }. Each question carries full per-record attribution (source, author, license, licenseVersion, licenseUrl, sourceId, url, modifications, lastModified) — identical shape to REST /api/v1/questions.

ATTRIBUTION REQUIRED if you redistribute. Credit each question using its own attribution object — see license + licenseUrl + modifications fields per record.

COMMON MISTAKES: not passing the cursor on subsequent calls (you'll re-read page 1); polling without updated_since when doing delta sync. Endpoint: https://quizbase.runriva.com/mcp
- quizbase_question_by_id (Get a single question by UUID) - Fetch one question with FULL per-record attribution (source, author, license, modifications, lastModified, sourceId, url) and `quality: "high" | "needs_review"` (always present — deep-link semantic means full row). USE WHEN: deep link to a question, full provenance lookup for redistribution, cache refresh, moderation inspection. INPUTS: id (UUID), lang (affects category.name and label translations only). 404 returned via {question: null, error: "not_found"} — id may be invalid, pending/rejected, canonical-duplicate, or tombstoned. Endpoint: https://quizbase.runriva.com/mcp
- quizbase_stats (Get public catalog statistics) - Public catalog counters with live breakdowns by language, source, category, difficulty, topic, tag.

USE WHEN: showing catalog overview, picking a category programmatically, building landing copy, deciding "do we have enough X-content for this quiz".

OUTPUT FIELDS:
- total: approved questions in 'en' + 'pl'.
- byLanguage: { en: N, pl: N }.
- bySource: { entityq: N, mintaka: N, 'kqa-pro': N, ... } — 12 keys, one per source database.
- byDifficulty: { trivial: N, easy: N, medium: N, hard: N, expert: N, unrated: N } — null difficulty mapped to 'unrated'. trivial/expert populated by LLM calibration.
- byCategory: top 24 with localized names.
- byTopic / byTag: top 30 curated topics + top 30 tags with localized labels.
- meta: { generatedAt: ISO 8601, language }.

INPUTS: lang (default "en") affects byCategory[].name and byTopic[].label / byTag[].label.

DATA FRESHNESS: snapshot regenerated daily (~03:00 UTC) + on demand after batch imports. generatedAt shows when. Counts stable ±0.01% between snapshots.

COMMON MISTAKES: polling stats every request (cache it on your side; 5-min Redis TTL on ours); treating bySource keys as stable enum (use quizbase_languages / quizbase_categories for canonical input enums). Endpoint: https://quizbase.runriva.com/mcp
- quizbase_topics (List curated topics with aliases) - Discover curated topics (2,184 entries with aliases). USE WHEN: planning a multi-round quiz, exploring "what is available about X", showing topic browser. Sorted by count DESC, slug ASC. Cursor-paginated. INPUTS: q (substring on label/alias), kind (tag|subcategory), cursor, limit (max 500). Endpoint: https://quizbase.runriva.com/mcp
- quizbase_topic_by_slug (Get curated topic detail with facets) - Fetch one curated topic with facets (byCategory, byDifficulty, byLanguage, coOccurringTags, coOccurringSubcategories) and 3 sample questions. USE WHEN: zooming into a topic, deciding multi-round quiz structure. Returns {topic: null, error: "not_found"} when slug is unknown. Endpoint: https://quizbase.runriva.com/mcp
- quizbase_tags (List raw tags with counts) - Raw tag dump (10k+ entries) with display label and question count. USE WHEN: building a tag picker, searching "is X a tag", running analytics. Curated higher-level groupings → quizbase_topics. INPUTS: q (substring), cursor, limit (max 500). Endpoint: https://quizbase.runriva.com/mcp
- quizbase_subcategories (List raw subcategories with counts) - Raw subcategory dump (LLM-organic kebab-case, middle taxonomy layer between category and tags) with display label and count. USE WHEN: navigating between top-level category and individual tags, exploring topic structure. Filter questions via quizbase_random?subcategory=<slug>. INPUTS: q, cursor, limit (max 500). Endpoint: https://quizbase.runriva.com/mcp
- quizbase_categories (List all top-level categories) - List of 24 top-level categories with i18n labels. USE WHEN: building a category picker, validating ?category= input. Stable enum (rarely changes). For higher-resolution browsing → quizbase_subcategories or quizbase_topics. Endpoint: https://quizbase.runriva.com/mcp
- quizbase_languages (List supported languages with counts) - Returns supported language whitelist (ISO 639-1) with question counts per language. USE WHEN: showing language picker, validating ?lang= input, deciding fallback. Day 1: en + pl. Endpoint: https://quizbase.runriva.com/mcp
- quizbase_regions (List region codes (cultural affinity) with counts) - Discover region codes used by the catalog. **Cultural affinity** — a question is tagged with a region if residents of that country, or members of that cultural/religious group, are statistically more likely to know the answer (NOT geography of the subject). USE WHEN: planning a quiz targeting users from a specific country or cultural background, exploring "what regions are represented". OUTPUT: array of {code, kind, label, count} sorted by count DESC. INPUTS: lang (en|pl), q (substring on code/label), kind (country|cultural), cursor, limit (max 500). Pair with quizbase_random or quizbase_list using `regions:[...]` to fetch matching questions. Endpoint: https://quizbase.runriva.com/mcp
- quizbase_report (Submit a content correction or copyright report) - Submit a content correction, copyright concern, or factual error report. USE WHEN: user (via your interface) flags a wrong answer, broken translation, attribution issue, or DMCA concern. INPUTS: at least one of (questionId UUID, questionText, questionUrl), type (translation|factual|inappropriate|attribution|other), comment (optional, max 2000), reporterEmail (optional). OUTPUT on success: {ok:true, reportId}. On failure the result is marked isError:true with structuredContent {error, message} — error codes: invalid_input, not_found, rate_limit_exceeded (per-IP 5/min), internal_error. Endpoint: https://quizbase.runriva.com/mcp

## Resources
- mcp://quizbase/categories - Categories catalog (English) Live list of 24 top-level categories with English labels. Stable enum (rarely changes). For other languages use the `quizbase_categories` tool with `lang: "pl"`. MIME type: application/json
- mcp://quizbase/languages - Supported languages Supported language whitelist (ISO 639-1) with question counts per language. Day 1: en + pl. Use as the source of truth for the `lang` parameter in tools and resources. MIME type: application/json
- mcp://quizbase/topics/top-100 - Top-100 curated topics by question count Top 100 curated topics sorted by question count DESC (English labels). USE WHEN: showing "what is popular" on a landing or topic browser, picking starting topics for an agent. For other languages or filtering use the `quizbase_topics` tool. Updated when the discovery pre-aggregates are refreshed. MIME type: application/json

## Prompts
- build_quiz - Build a multi-round quiz on any topic Generate a structured multi-round quiz with questions per round. Resolves topic via quizbase_topics, then fetches questions per round via quizbase_random with attribution. Arguments: topic, lang, difficulty, rounds, questions_per_round
- explore_topic - Discursively explore a topic Investigate what is in the catalog about a topic — facets (by category, difficulty, language, co-occurring tags), sample questions, and related curated topics. Use quizbase_topic_by_slug for the heavy lifting and present a concise summary. Arguments: topic, lang
- warmup_round - Quick 5-question warm-up round Lightweight icebreaker — 5 mixed-difficulty questions on a topic (or random if no topic given). Single quizbase_random call, no multi-round orchestration. Arguments: topic, lang
- client_mechanics_patterns - Build a client-side quiz mechanic on top of stable question IDs Walkthrough how to assemble QuizBase primitives (quizbase_random + quizbase_question_by_id + quizbase_list) into common client-side mechanics without server state. Stable UUID id per question enables daily challenges, multi-language sync, anti-cheat, Anki cards, multiplayer. Arguments: mechanic, lang

## Metadata
- Owner: com.runriva.quizbase
- Version: 0.1.1
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 24, 2026
- Source: https://registry.modelcontextprotocol.io