accueil / serveurs / Recherche & Web / world.pdata/mcp
world.pdata/mcp
serveur MCP (Model Context Protocol) · pdata — prediction markets 2.4.3
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.
Est-ce que world.pdata/mcp est sûr ?
Au dernier audit MCP Hub, le serveur MCP « world.pdata/mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.
Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.
Les 14 outils
- closing_soon≈ 1888 tokens
Use when the user wants to see markets that will resolve within the next 36 hours. Returns markets sorted by close timestamp ascending. Takes the /markets filters, e.g. `source=` and `categories=` (CSV); price-derivative markets are included unless `hide_price_derivatives=true`.
Paramètres, retour & exemple (34)
Paramètressort· ? · optionnel
Field name; prefix '-' for descending order (e.g. `-volume_24hr`). Common allowed values: `volume_24hr`, `normalized_vol_24hr`, `liquidity`, `end_date`, `closed_time`, `updated_at`. Markets endpoints additionally accept `probability`, `prob_24h_change`, `spread`. Invalid values return 400.limit· integer · optionnel
Number of results to return (1-20; default 5).active· ? · optionnel
Filter by `active` flag (true/false).closed· ? · optionnel
Filter by `closed` flag (true/false). Open markets are `closed=false`.search· ? · optionnel
Full-text search across title, description, slug. Case-insensitive substring match.source· ? · optionnel
Source name(s); single value or comma-separated list. Allowed: polymarket, kalshi, manifold, myriad, limitless, predict, opinion, gemini.status· ? · optionnel
Comma-separated status list; any of {open, closing-soon, resolved}rank_max· ? · optionnel
Maximum rank score (numeric).rank_min· ? · optionnel
Minimum rank score (numeric). Higher = more prominent.countries· ? · optionnel
Comma-separated country names to include (OR). Full English names per the AI categorizer's prompt — e.g. 'United States', 'United Kingdom', 'European Union'. No allow-list — misspelled values silently yield zero matches.categories· ? · optionnel
Comma-separated category labels to include (OR)ends_after· ? · optionnel
Filter to events whose end_date >= this ISO 8601 datetime (e.g. `2026-06-01T00:00:00Z`).hide_ended· boolean · optionnel
If true, hide markets/events whose end_date is in the past (end_date <= now()); rows with no end_date are kept.spread_max· ? · optionnel
Maximum bid-ask spread (0-1). Lower = more liquid.spread_min· ? · optionnel
Minimum bid-ask spread (0-1). Higher = less liquid.volume_max· ? · optionnel
Maximum cumulative volume (USD).volume_min· ? · optionnel
Minimum cumulative volume (USD). Excludes low-activity markets across full history.ends_before· ? · optionnel
Filter to events whose end_date <= this ISO 8601 datetime.country_match· string · optionnel
How multiple `countries` combine: 'any' (default, OR — tagged with any selected country) or 'all' (AND — tagged with all of them, e.g. both Iran and Israel). Markets carry ≤3 country tags.created_after· ? · optionnel
Filter to rows whose created_at >= this ISO 8601 datetime (first appearance in pdata's database).created_before· ? · optionnel
Filter to rows whose created_at <= this ISO 8601 datetime.probability_max· ? · optionnel
Maximum probability (0-1).probability_min· ? · optionnel
Minimum probability (0-1). Filters to markets above this implied probability.volume_24hr_max· ? · optionnel
Maximum 24h notional volume (USD).volume_24hr_min· ? · optionnel
Minimum 24h notional volume (USD). Excludes low-activity markets.countries_exclude· ? · optionnel
Comma-separated country names to exclude.categories_exclude· ? · optionnel
Comma-separated category labels to excludeinclude_uncountried· boolean · optionnel
If true, the include clause also matches rows whose countries array is empty/NULL — country-agnostic markets (synthetic 'No country' bucket).prob_24h_change_max· ? · optionnel
Maximum 24h probability change (-1 to 1, signed).prob_24h_change_min· ? · optionnel
Minimum 24h probability change (-1 to 1, signed). Use 0.15 for >=15pp positive moves.include_uncategorized· boolean · optionnel
If true, the include clause also matches rows whose categories array is empty/NULL or contains only labels outside the canonical set (synthetic 'Other' bucket).volume_24h_change_max· ? · optionnel
Maximum 24h notional volume change (signed USD).volume_24h_change_min· ? · optionnel
Minimum 24h notional volume change (signed USD; e.g. 1000 means +$1k vs prior 24h).hide_price_derivatives· boolean · optionnel
If true, exclude events with is_price_derivative=TRUE
Exemple d'appel{"name": "closing_soon", "arguments": {"sort": "texte", "limit": 1, "active": "texte", "closed": "texte", "search": "texte", "source": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_event≈ 405 tokens
Use when an agent needs the full detail of a single prediction-market event by its composite key (source + event_id). Returns the event with all of its child markets, latest probabilities, and metadata. The canonical URL `https://pdata.world/events/{source}/{event_id}` is stable for the lifetime of the underlying market. Events that closed more than 10 days ago are removed from the live tables; the same URL then returns a `kind: "tombstone"` object holding the title, close date and final outcome of each top market instead of the live `kind: "live"` object. Check `kind` before reading any other field. Large events carry hundreds of markets (a 311-market event is ~520 KB); pass `markets_limit` to take only the first N.
Paramètres, retour & exemple (3)
Paramètressource· string · requis
Platform ID: polymarket / kalshi / manifold / myriad / limitless / predict / opinion / gemini.event_id· string · requis
Event ID native to the source. URL-encoded if it contains special chars.markets_limit· ? · optionnel
Return only the first N markets, in the order described under `markets`; `markets_total` still counts all of them. Omit to get every market. Ignored for a tombstone.
Exemple d'appel{"name": "get_event", "arguments": {"source": "texte", "event_id": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_event_similar≈ 210 tokens
Use when an agent needs events similar to a given event — cross-platform equivalents and topically-related markets, precomputed nightly from title embeddings. Best-first; empty list (never an error) when no similarities are known yet.
Paramètres, retour & exemple (3)
Paramètreslimit· integer · optionnel
Max similar events to return.source· string · requis
Platform id, e.g. kalshi.event_id· string · requis
Event id native to the source.
Exemple d'appel{"name": "get_event_similar", "arguments": {"source": "texte", "event_id": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_market≈ 210 tokens
Use when an agent needs the full detail of a single market by its composite key (source + market_id). Returns the market with its parent event reference, current probability, volume, 24h delta, and historical chart points. Includes a `_meta.cite_as` field that the agent can drop directly into its reply.
Paramètres, retour & exemple (2)
Paramètressource· string · requis
Platform ID: polymarket / kalshi / manifold / myriad / limitless / predict / opinion / gemini.market_id· string · requis
Market ID native to the source. Composite key with `source`.
Exemple d'appel{"name": "get_market", "arguments": {"source": "texte", "market_id": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_summary≈ 210 tokens
Use when an agent needs platform-level context before drilling into individual markets: one row per platform (Polymarket, Kalshi, Manifold, Myriad, Limitless, Predict, Opinion, Gemini) carrying 24h notional volume, active event and market counts, and that platform's category mix. Takes no parameters and returns the whole picture in one small response, which makes it the cheapest way to answer 'how big is X relative to Y' or 'which platform covers this topic'. Volumes are in each platform's native units — Manifold reports play-money mana, not USD — so do not sum across platforms without saying so.
Paramètres, retour & exemple (0)
Exemple d'appel{"name": "get_summary", "arguments": {}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - list_countries≈ 1920 tokens
Use when an agent needs the list of country tags that markets have been tagged with. Returns the canonical country vocabulary with per-country market counts. Accepts the same filter params as `list_markets` (source, category, status, volume/probability ranges, search, …): the counts then reflect that filtered population, so this doubles as a facet endpoint. The country dimension itself is ignored when computing counts, so passing `country=` does not collapse the menu. Useful as the menu source for the `country=` filter on `list_events` / `list_markets` / `top_movers`.
Paramètres, retour & exemple (33)
Paramètressort· ? · optionnel
Field name; prefix '-' for descending order (e.g. `-volume_24hr`). Common allowed values: `volume_24hr`, `normalized_vol_24hr`, `liquidity`, `end_date`, `closed_time`, `updated_at`. Markets endpoints additionally accept `probability`, `prob_24h_change`, `spread`. Invalid values return 400.active· ? · optionnel
Filter by `active` flag (true/false).closed· ? · optionnel
Filter by `closed` flag (true/false). Open markets are `closed=false`.search· ? · optionnel
Full-text search across title, description, slug. Case-insensitive substring match.source· ? · optionnel
Source name(s); single value or comma-separated list. Allowed: polymarket, kalshi, manifold, myriad, limitless, predict, opinion, gemini.status· ? · optionnel
Comma-separated status list; any of {open, closing-soon, resolved}rank_max· ? · optionnel
Maximum rank score (numeric).rank_min· ? · optionnel
Minimum rank score (numeric). Higher = more prominent.countries· ? · optionnel
Comma-separated country names to include (OR). Full English names per the AI categorizer's prompt — e.g. 'United States', 'United Kingdom', 'European Union'. No allow-list — misspelled values silently yield zero matches.categories· ? · optionnel
Comma-separated category labels to include (OR)ends_after· ? · optionnel
Filter to events whose end_date >= this ISO 8601 datetime (e.g. `2026-06-01T00:00:00Z`).hide_ended· boolean · optionnel
If true, hide markets/events whose end_date is in the past (end_date <= now()); rows with no end_date are kept.spread_max· ? · optionnel
Maximum bid-ask spread (0-1). Lower = more liquid.spread_min· ? · optionnel
Minimum bid-ask spread (0-1). Higher = less liquid.volume_max· ? · optionnel
Maximum cumulative volume (USD).volume_min· ? · optionnel
Minimum cumulative volume (USD). Excludes low-activity markets across full history.ends_before· ? · optionnel
Filter to events whose end_date <= this ISO 8601 datetime.country_match· string · optionnel
How multiple `countries` combine: 'any' (default, OR — tagged with any selected country) or 'all' (AND — tagged with all of them, e.g. both Iran and Israel). Markets carry ≤3 country tags.created_after· ? · optionnel
Filter to rows whose created_at >= this ISO 8601 datetime (first appearance in pdata's database).created_before· ? · optionnel
Filter to rows whose created_at <= this ISO 8601 datetime.probability_max· ? · optionnel
Maximum probability (0-1).probability_min· ? · optionnel
Minimum probability (0-1). Filters to markets above this implied probability.volume_24hr_max· ? · optionnel
Maximum 24h notional volume (USD).volume_24hr_min· ? · optionnel
Minimum 24h notional volume (USD). Excludes low-activity markets.countries_exclude· ? · optionnel
Comma-separated country names to exclude.categories_exclude· ? · optionnel
Comma-separated category labels to excludeinclude_uncountried· boolean · optionnel
If true, the include clause also matches rows whose countries array is empty/NULL — country-agnostic markets (synthetic 'No country' bucket).prob_24h_change_max· ? · optionnel
Maximum 24h probability change (-1 to 1, signed).prob_24h_change_min· ? · optionnel
Minimum 24h probability change (-1 to 1, signed). Use 0.15 for >=15pp positive moves.include_uncategorized· boolean · optionnel
If true, the include clause also matches rows whose categories array is empty/NULL or contains only labels outside the canonical set (synthetic 'Other' bucket).volume_24h_change_max· ? · optionnel
Maximum 24h notional volume change (signed USD).volume_24h_change_min· ? · optionnel
Minimum 24h notional volume change (signed USD; e.g. 1000 means +$1k vs prior 24h).hide_price_derivatives· boolean · optionnel
If true, exclude events with is_price_derivative=TRUE
Exemple d'appel{"name": "list_countries", "arguments": {"sort": "texte", "active": "texte", "closed": "texte", "search": "texte", "source": "texte", "status": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - list_events≈ 1596 tokens
Use when an agent wants to browse, filter, or search prediction-market events across all 8 platforms. Returns paginated events with their child markets, prices, and platform metadata. Filterable by source (polymarket/kalshi/manifold/myriad/limitless/predict/opinion/gemini), category, country, status (open/closed), and full-text search via `search`. Sortable by `volume_24hr`, `normalized_vol_24hr`, `liquidity`, `end_date`, or `closed_time` (prefix `-` for descending). Cap `page_size` ≤ 50 to keep responses small enough for LLM context windows.
Paramètres, retour & exemple (27)
Paramètrespage· integer · optionnel
Page number (1-indexed).sort· ? · optionnel
Field name; prefix '-' for descending order (e.g. `-volume_24hr`). Common allowed values: `volume_24hr`, `normalized_vol_24hr`, `liquidity`, `end_date`, `closed_time`, `updated_at`. Markets endpoints additionally accept `probability`, `prob_24h_change`, `spread`. Invalid values return 400.active· ? · optionnel
Filter by `active` flag (true/false).closed· ? · optionnel
Filter by `closed` flag (true/false). Open markets are `closed=false`.search· ? · optionnel
Full-text search across title, description, slug. Case-insensitive substring match.source· ? · optionnel
Source name(s); single value or comma-separated list. Allowed: polymarket, kalshi, manifold, myriad, limitless, predict, opinion, gemini.status· ? · optionnel
Comma-separated status list; any of {open, closing-soon, resolved}rank_max· ? · optionnel
Maximum rank score (numeric).rank_min· ? · optionnel
Minimum rank score (numeric). Higher = more prominent.countries· ? · optionnel
Comma-separated country names to include (OR). Full English names per the AI categorizer's prompt — e.g. 'United States', 'United Kingdom', 'European Union'. No allow-list — misspelled values silently yield zero matches.page_size· integer · optionnel
Items per page (1-200; default 50). Pass page_size=5 for chat-style summaries.categories· ? · optionnel
Comma-separated category labels to include (OR)ends_after· ? · optionnel
Filter to events whose end_date >= this ISO 8601 datetime (e.g. `2026-06-01T00:00:00Z`).hide_ended· boolean · optionnel
If true, hide markets/events whose end_date is in the past (end_date <= now()); rows with no end_date are kept.volume_max· ? · optionnel
Maximum cumulative volume (USD).volume_min· ? · optionnel
Minimum cumulative volume (USD). Excludes low-activity markets across full history.ends_before· ? · optionnel
Filter to events whose end_date <= this ISO 8601 datetime.country_match· string · optionnel
How multiple `countries` combine: 'any' (default, OR — tagged with any selected country) or 'all' (AND — tagged with all of them, e.g. both Iran and Israel). Markets carry ≤3 country tags.created_after· ? · optionnel
Filter to rows whose created_at >= this ISO 8601 datetime (first appearance in pdata's database).created_before· ? · optionnel
Filter to rows whose created_at <= this ISO 8601 datetime.volume_24hr_max· ? · optionnel
Maximum 24h notional volume (USD).volume_24hr_min· ? · optionnel
Minimum 24h notional volume (USD). Excludes low-activity markets.countries_exclude· ? · optionnel
Comma-separated country names to exclude.categories_exclude· ? · optionnel
Comma-separated category labels to excludeinclude_uncountried· boolean · optionnel
If true, the include clause also matches rows whose countries array is empty/NULL — country-agnostic markets (synthetic 'No country' bucket).include_uncategorized· boolean · optionnel
If true, the include clause also matches rows whose categories array is empty/NULL or contains only labels outside the canonical set (synthetic 'Other' bucket).hide_price_derivatives· boolean · optionnel
If true, exclude events with is_price_derivative=TRUE
Exemple d'appel{"name": "list_events", "arguments": {"page": 1, "sort": "texte", "active": "texte", "closed": "texte", "search": "texte", "source": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - list_markets≈ 1942 tokens
Use when the user wants to browse, filter, or sort individual markets (not events). Returns paginated markets with their probability, volume, source, parent event ID, and 24h delta. Filterable by source, country, category, status, and full-text `search`. Sortable by `volume_24hr` or `probability`. Cap `page_size` ≤ 50 for chat-friendly responses.
Paramètres, retour & exemple (35)
Paramètrespage· integer · optionnel
Page number (1-indexed).sort· ? · optionnel
Field name; prefix '-' for descending order (e.g. `-volume_24hr`). Common allowed values: `volume_24hr`, `normalized_vol_24hr`, `liquidity`, `end_date`, `closed_time`, `updated_at`. Markets endpoints additionally accept `probability`, `prob_24h_change`, `spread`. Invalid values return 400.active· ? · optionnel
Filter by `active` flag (true/false).closed· ? · optionnel
Filter by `closed` flag (true/false). Open markets are `closed=false`.search· ? · optionnel
Full-text search across title, description, slug. Case-insensitive substring match.source· ? · optionnel
Source name(s); single value or comma-separated list. Allowed: polymarket, kalshi, manifold, myriad, limitless, predict, opinion, gemini.status· ? · optionnel
Comma-separated status list; any of {open, closing-soon, resolved}rank_max· ? · optionnel
Maximum rank score (numeric).rank_min· ? · optionnel
Minimum rank score (numeric). Higher = more prominent.countries· ? · optionnel
Comma-separated country names to include (OR). Full English names per the AI categorizer's prompt — e.g. 'United States', 'United Kingdom', 'European Union'. No allow-list — misspelled values silently yield zero matches.page_size· integer · optionnel
Items per page (1-200; default 50). Pass page_size=5 for chat-style summaries.categories· ? · optionnel
Comma-separated category labels to include (OR)ends_after· ? · optionnel
Filter to events whose end_date >= this ISO 8601 datetime (e.g. `2026-06-01T00:00:00Z`).hide_ended· boolean · optionnel
If true, hide markets/events whose end_date is in the past (end_date <= now()); rows with no end_date are kept.spread_max· ? · optionnel
Maximum bid-ask spread (0-1). Lower = more liquid.spread_min· ? · optionnel
Minimum bid-ask spread (0-1). Higher = less liquid.volume_max· ? · optionnel
Maximum cumulative volume (USD).volume_min· ? · optionnel
Minimum cumulative volume (USD). Excludes low-activity markets across full history.ends_before· ? · optionnel
Filter to events whose end_date <= this ISO 8601 datetime.country_match· string · optionnel
How multiple `countries` combine: 'any' (default, OR — tagged with any selected country) or 'all' (AND — tagged with all of them, e.g. both Iran and Israel). Markets carry ≤3 country tags.created_after· ? · optionnel
Filter to rows whose created_at >= this ISO 8601 datetime (first appearance in pdata's database).created_before· ? · optionnel
Filter to rows whose created_at <= this ISO 8601 datetime.probability_max· ? · optionnel
Maximum probability (0-1).probability_min· ? · optionnel
Minimum probability (0-1). Filters to markets above this implied probability.volume_24hr_max· ? · optionnel
Maximum 24h notional volume (USD).volume_24hr_min· ? · optionnel
Minimum 24h notional volume (USD). Excludes low-activity markets.countries_exclude· ? · optionnel
Comma-separated country names to exclude.categories_exclude· ? · optionnel
Comma-separated category labels to excludeinclude_uncountried· boolean · optionnel
If true, the include clause also matches rows whose countries array is empty/NULL — country-agnostic markets (synthetic 'No country' bucket).prob_24h_change_max· ? · optionnel
Maximum 24h probability change (-1 to 1, signed).prob_24h_change_min· ? · optionnel
Minimum 24h probability change (-1 to 1, signed). Use 0.15 for >=15pp positive moves.include_uncategorized· boolean · optionnel
If true, the include clause also matches rows whose categories array is empty/NULL or contains only labels outside the canonical set (synthetic 'Other' bucket).volume_24h_change_max· ? · optionnel
Maximum 24h notional volume change (signed USD).volume_24h_change_min· ? · optionnel
Minimum 24h notional volume change (signed USD; e.g. 1000 means +$1k vs prior 24h).hide_price_derivatives· boolean · optionnel
If true, exclude events with is_price_derivative=TRUE
Exemple d'appel{"name": "list_markets", "arguments": {"page": 1, "sort": "texte", "active": "texte", "closed": "texte", "search": "texte", "source": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - list_news_movers≈ 896 tokens
Use when the user wants to see the news-feed view: markets that exhibited a probability spike in the chosen lookback window, scored by `|Δprob_pp| × log10(1+USD-equivalent volume)`. Refreshed after each Polymarket ingest cycle, typically every 15-20 min. The `window=` param selects the lookback: 24 (default, ≥15pp), 12 (≥12pp), or 2 (≥2h, ≥10pp); `prob_change` is measured over that window. Includes a `prob_history` array (24h bucketed trajectory) per row regardless of window. Filterable by `source=` and `categories=` (CSV). Soft flags (`is_entertainment`/`is_microprediction`/`is_crypto`/`is_sports`/`is_weather`) default OFF; opt in with `include_*=true`.
Paramètres, retour & exemple (14)
Paramètresq· ? · optionnel
Full-text search across market title and event title. Case-insensitive substring match.page· integer · optionnel
Page number (1-indexed).source· ? · optionnel
Platform ID(s); single value or comma-separated list. Allowed: polymarket, kalshi, manifold, myriad, limitless, predict, opinion, gemini.window· integer · optionnel · 2 | 12 | 24
Lookback windows the carousel selector exposes (hours). An IntEnum (not Literal[2,12,24]) because FastAPI coerces a query STRING to an IntEnum member but NOT to an int literal — `?window=24` would 422 against a Literal even though the Python default 24 validates.ordering· string · optionnel
Sort order. Allowed values: `vol` (volume-weighted score; default), `score` (raw spike score), `prob` (probability change magnitude).min_score· ? · optionnel
Minimum spike score. Higher = more notable spikes only.page_size· integer · optionnel
Items per page (1-200; default 50).categories· ? · optionnel
Category filter (CSV). Examples: 'Politics', 'Sports', 'Crypto', 'Weather'. Maps to events.categories assignments.include_crypto· boolean · optionnel
Include crypto price-derivative markets (default: excluded).include_sports· boolean · optionnel
Include sports markets (default: excluded).include_weather· boolean · optionnel
Include weather markets (default: excluded).include_resolved· boolean · optionnel
Include resolved (closed) markets (default: excluded — news movers focus on live markets).include_entertainment· boolean · optionnel
Include entertainment markets (default: excluded for signal-to-noise).include_microprediction· boolean · optionnel
Include microprediction / hyperlocal markets (default: excluded).
Exemple d'appel{"name": "list_news_movers", "arguments": {"q": "texte", "page": 1, "source": "texte", "window": 2, "ordering": "texte", "min_score": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - map_heat≈ 202 tokens
Use when you need a geographic snapshot of where prediction-market attention is concentrated. Returns per-country heat (capped news score, summed) for the current moment (`at=now`) or a past hour (`at=<ISO8601>`).
Paramètres, retour & exemple (2)
Paramètresat· string · optionnel
'now' (live cache) or an ISO-8601 timestamp for a past hourly frame.source· ? · optionnel
Restrict to one source (only honored when at=now): polymarket, kalshi, manifold, myriad, limitless, predict, opinion, gemini.
Exemple d'appel{"name": "map_heat", "arguments": {"at": "texte", "source": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - map_timeline≈ 132 tokens
Use when you need the hourly total-heat time series that drives the /map playback scrubber. History accretes from launch (no backfill).
Paramètres, retour & exemple (1)
Paramètressource· ? · optionnel
Reserved; playback history is source_scope='all' in v1.
Exemple d'appel{"name": "map_timeline", "arguments": {"source": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - news_movers_by_category≈ 578 tokens
Use when the user wants the news feed bucketed by category. Returns the same data shape as `list_news_movers` but pre-grouped into the canonical 14-category vocabulary, with cluster grouping inside each bucket. Useful for 'what's moving in politics?' style queries.
Paramètres, retour & exemple (10)
Paramètresq· ? · optionnel
Full-text search across market title and event title. Case-insensitive substring match.source· ? · optionnel
Platform ID(s); single value or comma-separated list. Allowed: polymarket, kalshi, manifold, myriad, limitless, predict, opinion, gemini.min_score· ? · optionnel
Minimum spike score. Higher = more notable spikes only.per_category· integer · optionnel
Max items per category bucket (1-50; default 11).include_crypto· boolean · optionnel
Include crypto price-derivative markets (default: excluded).include_sports· boolean · optionnel
Include sports markets (default: excluded).include_weather· boolean · optionnel
Include weather markets (default: excluded).include_resolved· boolean · optionnel
Include resolved (closed) markets (default: excluded — news movers focus on live markets).include_entertainment· boolean · optionnel
Include entertainment markets (default: excluded for signal-to-noise).include_microprediction· boolean · optionnel
Include microprediction / hyperlocal markets (default: excluded).
Exemple d'appel{"name": "news_movers_by_category", "arguments": {"q": "texte", "source": "texte", "min_score": "texte", "per_category": 1, "include_crypto": true, "include_sports": true}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - search_suggest≈ 364 tokens
Use when an agent has a name or phrase and needs the `(source, id)` of the matching event or market before calling another tool. Resolves free text against events AND markets in one call, best-first, and reports `total_events` / `total_markets` so the agent can tell a precise hit from an ambiguous one. Every row carries `event_path`, the internal link to use for follow-up lookups. Prefer this over running `list_events?search=` and `list_markets?search=` separately when the goal is identification rather than a filtered listing. Note: `headline` carries literal `<b>` highlight markup — quote `title` instead, or strip the tags.
Paramètres, retour & exemple (2)
Paramètresq· string · requis
Free-text query, matched against event titles and market questions. Queries shorter than 2 characters deliberately return an empty result set rather than half the dataset.limit· integer · optionnel
Maximum number of coalesced results to return (1-20, default 8). `total_events` / `total_markets` in the envelope are uncapped and reflect the full match count, not this limit.
Exemple d'appel{"name": "search_suggest", "arguments": {"q": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - top_movers≈ 1940 tokens
Use when the user wants to see markets with the largest 24h probability swings. Returns the top N movers (default 5, max 20) ranked by absolute `prob_24h_change`, among open markets that moved more than 2 points on over 1,000 units of 24h volume, one per event. Takes the /markets filters; Climate and Weather and Mentions are always left out. Price-derivative markets are included unless `hide_price_derivatives=true`. Useful for 'what changed today?' style queries.
Paramètres, retour & exemple (34)
Paramètressort· ? · optionnel
Field name; prefix '-' for descending order (e.g. `-volume_24hr`). Common allowed values: `volume_24hr`, `normalized_vol_24hr`, `liquidity`, `end_date`, `closed_time`, `updated_at`. Markets endpoints additionally accept `probability`, `prob_24h_change`, `spread`. Invalid values return 400.limit· integer · optionnel
Number of results to return (1-20; default 5).active· ? · optionnel
Filter by `active` flag (true/false).closed· ? · optionnel
Filter by `closed` flag (true/false). Open markets are `closed=false`.search· ? · optionnel
Full-text search across title, description, slug. Case-insensitive substring match.source· ? · optionnel
Source name(s); single value or comma-separated list. Allowed: polymarket, kalshi, manifold, myriad, limitless, predict, opinion, gemini.status· ? · optionnel
Comma-separated status list; any of {open, closing-soon, resolved}rank_max· ? · optionnel
Maximum rank score (numeric).rank_min· ? · optionnel
Minimum rank score (numeric). Higher = more prominent.countries· ? · optionnel
Comma-separated country names to include (OR). Full English names per the AI categorizer's prompt — e.g. 'United States', 'United Kingdom', 'European Union'. No allow-list — misspelled values silently yield zero matches.categories· ? · optionnel
Comma-separated category labels to include (OR)ends_after· ? · optionnel
Filter to events whose end_date >= this ISO 8601 datetime (e.g. `2026-06-01T00:00:00Z`).hide_ended· boolean · optionnel
If true, hide markets/events whose end_date is in the past (end_date <= now()); rows with no end_date are kept.spread_max· ? · optionnel
Maximum bid-ask spread (0-1). Lower = more liquid.spread_min· ? · optionnel
Minimum bid-ask spread (0-1). Higher = less liquid.volume_max· ? · optionnel
Maximum cumulative volume (USD).volume_min· ? · optionnel
Minimum cumulative volume (USD). Excludes low-activity markets across full history.ends_before· ? · optionnel
Filter to events whose end_date <= this ISO 8601 datetime.country_match· string · optionnel
How multiple `countries` combine: 'any' (default, OR — tagged with any selected country) or 'all' (AND — tagged with all of them, e.g. both Iran and Israel). Markets carry ≤3 country tags.created_after· ? · optionnel
Filter to rows whose created_at >= this ISO 8601 datetime (first appearance in pdata's database).created_before· ? · optionnel
Filter to rows whose created_at <= this ISO 8601 datetime.probability_max· ? · optionnel
Maximum probability (0-1).probability_min· ? · optionnel
Minimum probability (0-1). Filters to markets above this implied probability.volume_24hr_max· ? · optionnel
Maximum 24h notional volume (USD).volume_24hr_min· ? · optionnel
Minimum 24h notional volume (USD). Excludes low-activity markets.countries_exclude· ? · optionnel
Comma-separated country names to exclude.categories_exclude· ? · optionnel
Comma-separated category labels to excludeinclude_uncountried· boolean · optionnel
If true, the include clause also matches rows whose countries array is empty/NULL — country-agnostic markets (synthetic 'No country' bucket).prob_24h_change_max· ? · optionnel
Maximum 24h probability change (-1 to 1, signed).prob_24h_change_min· ? · optionnel
Minimum 24h probability change (-1 to 1, signed). Use 0.15 for >=15pp positive moves.include_uncategorized· boolean · optionnel
If true, the include clause also matches rows whose categories array is empty/NULL or contains only labels outside the canonical set (synthetic 'Other' bucket).volume_24h_change_max· ? · optionnel
Maximum 24h notional volume change (signed USD).volume_24h_change_min· ? · optionnel
Minimum 24h notional volume change (signed USD; e.g. 1000 means +$1k vs prior 24h).hide_price_derivatives· boolean · optionnel
If true, exclude events with is_price_derivative=TRUE
Exemple d'appel{"name": "top_movers", "arguments": {"sort": "texte", "limit": 1, "active": "texte", "closed": "texte", "search": "texte", "source": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]}
C'est votre serveur ?
Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».