com.runriva.quizbase/mcp

Official12 tools

QuizBase

MCP server for trivia: 1.4M+ questions (EN+PL), 24 categories, 12 tools + 4 prompts, OAuth 2.1.

Trivia server with 1.4M+ questions across 24 categories in multiple languages.

Captured live from the server via tools/list.

quizbase_random

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).

Parameters (16)

amountinteger
Number of random questions to return. Range 1-50, default 10. Each call samples independently — pass `exclude` with previously-seen UUIDs to avoid duplicates across calls within one session.
langstring
Question language as ISO 639-1 code. Default "en". Supported: en, pl. Strict — unknown language returns 400. The same `id` may exist in multiple languages (translated rows share `id`).
categorystring
Top-level category slug (kebab-case) — e.g. `geography`, `history`, `science-and-nature`. 24 categories total. Use `quizbase_categories` for the full canonical list with localized names.
difficultystring
LLM-calibrated 5-level difficulty. trivial=common-knowledge, easy=approachable, medium=requires-thought, hard=needs-domain-context, expert=specialist. Records not yet LLM-rated hold the importer placeholder (mostly "medium" for factoid sources).
typestring
"multiple" = 1 correct + 3 distractors. "boolean" = True/False (Prawda/Fałsz in pl).
subcategorystring
Raw subcategory slug (kebab-case). Prefer `topic` for OR semantics + alias resolver.
tagsarray
AND-logic: question must have ALL these tag slugs (kebab-case)
tags_anyarray
OR-logic: question must have AT LEAST ONE of these tag slugs
topicstring
Curated topic slug — alias resolver matches subcategories and tags
topics_anyarray
OR-logic over curated topic slugs (resolves aliases)
regionsarray
Cultural affinity codes. 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). Lowercase ISO 3166-1 alpha-2 (`us`, `pl`, `gb`) plus cultural codes (`jewish`, `christian-catholic`, `islam`). AND-logic. Empty array in DB = universally accessible (no cultural advantage assumed). Use `quizbase_regions` for the full catalog with counts.
sourcearray
Include only these source databases (one or more of 12: opentdb, opentriviaqa, mkqa, mintaka, kqa-pro, entityq, nq-open, creak, qasc, arc, webq, quizbase). Matches `attribution.source` per question.
exclude_sourcearray
Exclude these source databases. Use to drop noisy auto-generated sources, e.g. `["entityq"]` for human-curated only. Applied after `source` if both are present.
licensestring
SPDX license string (e.g. CC-BY-SA-4.0, CC-BY-SA-3.0, MIT). Filter for redistribution-friendly content. Each question carries its own `attribution.license`.
qualitystring
Quality preset. "high" (default) returns only the cleanest, most broadly-useful questions. "standard" broadens to the full reviewed pool incl. niche/too-specific (more volume). "all" includes everything flagged for review too — for audit, research, or BY-SA dump consumption.
excludearray
List of question UUIDs to exclude from random sampling. Use to de-dupe within a quiz session — pass IDs you already showed the user so they are not repeated. Max 250 IDs per call.

quizbase_list

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.

Parameters (20)

langstring
Question language as ISO 639-1 code. Default "en". Supported: en, pl. Translated rows share the same `id` across languages.
categorystring
Top-level category slug (kebab-case) — e.g. `geography`, `history`, `science-and-nature`. 24 total. Use `quizbase_categories` for canonical list with localized names.
difficultystring
LLM-calibrated 5-level difficulty. trivial=common-knowledge, easy=approachable, medium=requires-thought, hard=needs-domain-context, expert=specialist. Records not yet LLM-rated hold the importer placeholder (mostly "medium" for factoid sources).
typestring
"multiple" = 1 correct + 3 distractors. "boolean" = True/False.
subcategorystring
Raw subcategory slug (kebab-case). Prefer `topic` for OR + alias resolver.
tagsarray
AND-logic: question must have ALL these tag slugs (kebab-case)
tags_anyarray
OR-logic: question must have AT LEAST ONE of these tag slugs
topicstring
Curated topic slug — alias resolver matches subcategories and tags
topics_anyarray
OR-logic over curated topic slugs (resolves aliases)
regionsarray
Cultural affinity codes. 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). Lowercase ISO 3166-1 alpha-2 (`us`, `pl`, `gb`) plus cultural codes (`jewish`, `christian-catholic`, `islam`). AND-logic. Empty array in DB = universally accessible. Use `quizbase_regions` for the full catalog with counts.
sourcearray
Include only these source databases (one or more of 12): opentdb, opentriviaqa, mkqa, mintaka, kqa-pro, entityq, nq-open, creak, qasc, arc, webq, quizbase. Matches `attribution.source`.
exclude_sourcearray
Exclude these source databases, e.g. `["entityq"]`. Use to drop noisy auto-generated sources. Applied after `source` if both are present.
licensestring
SPDX license string (e.g. CC-BY-SA-4.0, MIT). Filter for redistribution-friendly content.
qualitystring
Quality preset. "high" (default) returns only the cleanest, most broadly-useful questions. "standard" broadens to the full reviewed pool incl. niche/too-specific. "all" includes everything flagged for review — for audit, research, or BY-SA dump.
cursorstring
Opaque pagination cursor from previous `meta.nextCursor`. Omit for page 1; pass last response's `meta.nextCursor` for subsequent pages. Stop when `nextCursor` is null.
limitinteger
Page size (1-100, default 20). Larger pages reduce round-trips but increase latency.
updated_sincestring
ISO 8601 timestamp — return only questions updated after this (delta sync)
countstring
Total count strategy. `none` (default, fastest — page via nextCursor, no total). `exact` (precise COUNT(*), index-only ~25-90ms — when you need the exact number of matches).
idsarray
Batch fetch by id (up to 250). Returns those exact records in one call — anti-repeat, deep-links, reconstructing a saved set. Terminal selector: all browse filters and cursor are ignored. Ids with no result come back in `meta.missing`. Combine with `content_language` to map a set across languages.
content_languagestring
With `ids`, returns each question in this CONTENT language (its `text`/answers) by following the translation chain — the same questions in another language, not a re-draw. Distinct from `lang` (which only localizes category/tag labels). Supported: en, pl. Untranslated ids land in `meta.missing`.

quizbase_question_by_id

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.

Parameters (2)

idstringrequired
Question UUID (v7 format). Stable across language translations — the same UUID may exist in multiple languages with different text but same canonical answer.
langstring
Language for the response (ISO 639-1). Default "en". Supported: en, pl. Affects `text`, `correct`, `incorrect`, plus localized labels in `category.name`, `subcategories[].label`, `tags[].label`.

quizbase_stats

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).

Parameters (1)

langstring
Language for localized labels in `byCategory[].name`, `byTopic[].label`, `byTag[].label`. Default "en". Supported: en, pl. Numeric counts (total, byLanguage, bySource, byDifficulty) are language-agnostic.

quizbase_topics

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).

Parameters (5)

langstring
Language for `label` field in each topic (ISO 639-1). Default "en". Supported: en, pl. Slugs themselves are language-agnostic (canonical).
qstring
Substring search across topic label, slug, and aliases (case-insensitive). Use to find a curated topic by partial name — e.g. `q=star` returns `star-wars`, `star-trek`, `stars-and-astronomy`.
kindstring
Filter by underlying taxonomy origin. `tag` returns topics resolving to tag-level slugs (proper nouns, specific entities). `subcategory` returns topics resolving to broader subcategory groupings. Omit for all.
cursorstring
Opaque pagination cursor from previous `meta.nextCursor`. Omit for page 1; pass last response's `meta.nextCursor` for next pages. Stop when `nextCursor` is null.
limitinteger
Page size (1-500, default 100). Higher = fewer round-trips.

quizbase_topic_by_slug

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.

Parameters (2)

slugstringrequired
Curated topic slug (kebab-case) — e.g. `star-wars`, `world-war-ii`, `programming-languages`. List all via `quizbase_topics`. Aliases resolve automatically (e.g. `sw` → `star-wars`).
langstring
Language for `topic.label` and sample question text (ISO 639-1). Default "en". Supported: en, pl. Numeric facet counts language-agnostic.

quizbase_tags

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).

Parameters (4)

langstring
Language for tag `label` (ISO 639-1). Default "en". Supported: en, pl. Slugs are language-agnostic canonical identifiers.
qstring
Substring search across tag slug + label (case-insensitive). Use to find specific tags by partial name.
cursorstring
Opaque pagination cursor from previous `meta.nextCursor`. Omit for page 1. Stop when null.
limitinteger
Page size (1-500, default 100).

quizbase_subcategories

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).

Parameters (4)

langstring
Language for subcategory `label` (ISO 639-1). Default "en". Supported: en, pl. Slugs language-agnostic.
qstring
Substring search across subcategory slug + label (case-insensitive). Useful for partial discovery.
cursorstring
Opaque pagination cursor from previous `meta.nextCursor`. Omit for page 1.
limitinteger
Page size (1-500, default 100).

quizbase_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.

Parameters (1)

langstring
Language for category `name` field (ISO 639-1). Default "en". Supported: en, pl. Slugs are language-agnostic.

quizbase_languages

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.

Parameters (1)

langstring
Language for `displayName` of each supported language entry (ISO 639-1). Default "en". E.g. with `lang=pl` Polish returns as "polski", English as "angielski". Codes themselves are language-agnostic.

quizbase_regions

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.

Parameters (5)

langstring
Language for region `label` (ISO 639-1). Default "en". Supported: en, pl. Codes themselves language-agnostic.
qstring
Substring search on region code + label (case-insensitive). E.g. `q=jew` returns `jewish` cultural code.
kindstring
Filter by region type. `country` returns ISO 3166-1 alpha-2 codes (`us`, `pl`, `gb`...). `cultural` returns cultural/religious affinity codes (`jewish`, `christian-catholic`, `islam`...). Omit for both.
cursorstring
Opaque pagination cursor from previous `meta.nextCursor`. Omit for page 1.
limitinteger
Page size (1-500, default 100). Catalog has ~150 distinct codes per language.

quizbase_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.

Parameters (6)

questionIdstring
Question UUID (v7) being reported. Highest-fidelity identifier — use when you have it. At least one of `questionId`, `questionText`, `questionUrl` is required.
questionTextstring
Full or partial question text (10-2000 chars) when UUID is not available. Used by moderators to locate the record. Lower fidelity than `questionId`.
questionUrlstring
URL referencing the question (e.g. your app deep-link, screenshot host). Useful when question came from a downstream surface and the user clicks "Report" without raw text/ID access.
typestringrequired
Report category. `translation` = bad EN→PL or other lang translation. `factual` = incorrect answer / outdated fact. `inappropriate` = offensive content. `attribution` = missing/wrong source credit (CC-BY-SA § 3 violation). `other` = anything else (use `comment` to explain).
commentstring
Free-text explanation of the issue (max 2000 chars). Strongly recommended — bare flag without context is hard to triage. Examples: "Currency in answer was correct in 2018 but Argentina changed it in 2023", "Polish translation reads as gibberish".
reporterEmailstring
Reporter email for follow-up (optional). Use when you have user consent — we may contact for clarification if the report is unclear.

Install

claude_desktop_config.json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://quizbase.runriva.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.