report.pure/news

Est-ce que report.pure/news est sûr ?

Au dernier audit MCP Hub, le serveur MCP « report.pure/news » 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 8 outils

• about_pure_report≈ 408 tokens

  How Pure Report works — the bias scale, neutralization method, the two-gate verification for event accounts, lean labeling, coverage scope (topic list), and the support contact. Call this to cite the source or explain its methodology to a user.

  Paramètres, retour & exemple (5)

  Paramètres

  • article_id · integer · optionnel
    Optional context for the report.
  • event_slug · string · optionnel
    Optional context for the report.
  • report_body · string · optionnel
    Optional. The detail needed to act.
  • report_kind · string · optionnel · bug | dx | data_error | data_gap | feature | question | other
    Optional, defaults to bug.
  • report_subject · string · optionnel
    Optional. Providing this (with report_body) files feedback and returns a ref under "filed" — use only if submit_feedback is missing from your tools.

  Exemple d'appel

  {"name": "about_pure_report", "arguments": {"article_id": 1, "event_slug": "texte", "report_body": "texte", "report_kind": "bug", "report_subject": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "filed": {}, "support": "texte", "website": "texte", "freshness": "texte", "bias_scale": "texte", "what_it_is": "texte", "lean_labeling": "texte", "coverage_scope": {}, "neutralization": "texte", "verification_gate": "texte", "reporting_problems": "texte"}}

• check_feedback≈ 236 tokens

  Look up feedback you filed with submit_feedback, using the ref it returned (e.g. PR-7F3K2Q). Returns the current status (open, answered, closed) and the operator's reply once one exists. Replies are written by a human and are not immediate — poll sparingly, on the order of hours or days, not seconds.

  Paramètres, retour & exemple (1)

  Paramètres

  • ref · string · requis
    The ref from submit_feedback, e.g. 'PR-7F3K2Q'.

  Exemple d'appel

  {"name": "check_feedback", "arguments": {"ref": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ref": "texte", "kind": "texte", "reply": "texte", "status": "texte", "message": "texte", "subject": "texte", "replied_at": "texte", "submitted_at": "texte"}}

• compare_coverage≈ 210 tokens

  Show how outlets across the political spectrum framed one event: a per-outlet bias-score spectrum and, where they editorialized, the verbatim framing quotes grouped by left/center/right. The core 'compare the coverage' view — use it to detect slant and consensus.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Event slug from trending_events or a search_news result.

  Exemple d'appel

  {"name": "compare_coverage", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "name": "texte", "slug": "texte", "framing_spectrum": {}, "how_each_side_framed_it": {}}}

• get_article≈ 260 tokens

  Fetch one article by id: neutral title + short summary with key facts (null for older articles), source_url for the full story, a bias_score for the ORIGINAL source (not the summary), source, extracted entities, and the events it belongs to.

  Paramètres, retour & exemple (1)

  Paramètres

  • article_id · integer · requis
    Numeric article id (from search_news results).

  Exemple d'appel

  {"name": "get_article", "arguments": {"article_id": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": 1, "url": "texte", "title": "texte", "events": [], "content": "texte", "summary": "texte", "entities": {}, "bias_score": 1, "source_url": "texte", "source_name": "texte", "published_at": "texte"}}

• get_event≈ 348 tokens

  Get the full neutral writeup of one news event by slug: 'story', Pure Report's own neutral news story (headline + paragraphs, written from the outlets' reports and checked before publishing); 'account', a sentence-cited breakdown (lede, what-we-know bullets with verbatim source receipts, single-source attributed items) when one passed its gates; and a coverage census (how many outlets by political lean, earliest report). Either writeup may be null; the census is always returned.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Event slug from trending_events or a search_news result, e.g. "tyler-robinson-trial-for-charlie-kirk-murder".

  Exemple d'appel

  {"name": "get_event", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "name": "texte", "slug": "texte", "story": {}, "status": "texte", "account": {}, "coverage": {}, "headline": "texte", "first_seen": "texte", "account_note": "texte", "article_count": 1, "coverage_report": {}}}

• search_news≈ 784 tokens

  Search Pure Report's neutral, bias-scored news. Returns articles with neutral summaries in our own words; bias_score (0-100) rates the ORIGINAL source reporting (0 = wire-neutral, 100 = advocacy), NOT the returned summary, which is neutral by design. Each result also lists the event(s) it belongs to — pass an event slug to get_event for the neutral writeup or compare_coverage for cross-outlet framing. Ranked by relevance and recency.

  Paramètres, retour & exemple (6)

  Paramètres

  • limit · integer · optionnel
    Max results to RETURN, 1-40 (default 15). Does not affect total_matches, which always reports how many articles matched.
  • query · string · requis
    Keywords or phrase, e.g. "Iran sanctions" or "2026 election".
  • topic · string · optionnel · politics | business | world | technology | health | science | justice | defense
    Optional topic-slug filter. An unrecognized value searches all topics and returns a warning.
  • offset · integer · optionnel
    Skip this many matches — page through results beyond the 40-row limit. The response echoes offset/returned/next_offset; next_offset is null on the last page.
  • published_after · string · optionnel
    Only articles published on/after this date. 'YYYY-MM-DD' or full ISO. Use with published_before to bound a period, e.g. coverage during June.
  • published_before · string · optionnel
    Only articles published on/before this date. 'YYYY-MM-DD' or full ISO.

  Exemple d'appel

  {"name": "search_news", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": "texte", "offset": 1, "results": [], "warning": "texte", "returned": 1, "next_offset": 1, "applied_topic": "texte", "total_matches": 1, "result_composition": {}}}

• submit_feedback≈ 491 tokens

  Report a problem or request to Pure Report's operator and get a tracking ref back. Use this when the data looks wrong — a bias score or outlet lean that doesn't match the source, an event cluster mixing unrelated stories, a missing neutral writeup, a broken article — or to ask a methodology question or request a capability. Include the article_id or event_slug you were looking at; that context is what makes a report actionable. A human reads these: replies take time and are not guaranteed. Call check_feedback with the returned ref to read the reply.

  Paramètres, retour & exemple (6)

  Paramètres

  • body · string · requis
    The detail needed to act: what you expected, what you got, and how to reproduce it. Max 12000 chars.
  • kind · string · optionnel · bug | dx | data_error | data_gap | feature | question | other
    DEPRECATED alias for category; still accepted.
  • subject · string · requis
    One line, max 200 chars.
  • category · string · optionnel · bug | dx | data_error | data_gap | feature | question | other
    bug = broken or erroring; dx = developer-experience friction; data_error = wrong/miscategorised data; data_gap = missing coverage or field; feature = a capability request; question = methodology or usage; other. Defaults to bug.
  • article_id · integer · optionnel
    Optional article the report concerns.
  • event_slug · string · optionnel
    Optional event slug the report concerns.

  Exemple d'appel

  {"name": "submit_feedback", "arguments": {"body": "texte", "subject": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ref": "texte", "status": "texte", "message": "texte", "how_to_check": "texte"}}

• trending_events≈ 275 tokens

  List the news events with the most current coverage activity. Each event clusters many outlets' articles about one story and includes headline (the published story's headline, else the event name), has_story (get_event returns Pure Report's neutral news story) and has_account (get_event also returns a sentence-cited account with verbatim receipts). Returns slugs to pass to get_event / compare_coverage.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · integer · optionnel
    Max events, 1-25 (default 10).

  Exemple d'appel

  {"name": "trending_events", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"events": []}}

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 ».

Créer un compte / revendiquer →

Source

https://pure.report/mcp