newsflash

Real-time corroborated news events + 5-year archive, for agents. Free tier, no key.

使うべきか

品質と安全性

A
説明の品質
100%
スキーマの完全性
68%
命名の品質
96%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~1,124トークン数(ツール定義)
~1.3 KB一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 0.88%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "newsflash": {
      "url": "https://newsflash.sh/mcp"
    }
  }
}

リモートエンドポイント

https://newsflash.sh/mcpstreamable-http

できること

ツール一覧

ツール(5)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢get_events(q, semantic, source, category, from, ...)

Query the deduped news event graph by theme, source, category and time window. Returns events (many articles about one happening collapsed into one), each with a corroboration count and confidence score. This is the primary tool — prefer it over raw articles. For headlines, briefings, or 'what's happening' asks, pass min_sources: 2 (or 3 for high signal) — the raw recency feed is dominated by single-outlet local stories without it. ONE call is normally enough: trust each event's corroboration (distinct outlets), confidence (0-1; 1.0 = fully corroborated), and sources list as-is, and present the top events directly, including each event's url as its link — do NOT call get_event per item or re-verify counts (only drill in when the user wants EVERY outlet's link for one story). The corpus spans 260+ global outlets and a five-year archive (history visible depends on tier).

入力スキーマ

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free-text theme/keyword to match on headline + summary"
    },
    "semantic": {
      "type": "boolean",
      "description": "Rank by meaning (embedding similarity) instead of keyword match — requires q; better for concepts ('monetary easing') than exact strings"
    },
    "source": {
      "type": "string",
      "description": "Source slug, e.g. 'coindesk' (see list_sources)"
    },
    "category": {
      "type": "string",
      "enum": [
        "crypto",
        "tradfi",
        "business",
        "tech",
        "politics",
        "world",
        "science",
        "health",
        "energy",
        "sports"
      ],
      "description": "Source category"
    },
    "from": {
      "type": "string",
      "description": "Only events active on/after this date. ISO 8601 date/time, e.g. 2026-07-01 or 2026-07-01T00:00:00Z"
    },
    "to": {
      "type": "string",
      "description": "Only events active on/before this date. ISO 8601 date/time, e.g. 2026-07-01 or 2026-07-01T00:00:00Z"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Max events (default 15)"
    },
    "min_sources": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "description": "Only events corroborated by at least this many distinct outlets — use 2-3 for briefings/headlines to skip single-source noise"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_event(id)

Fetch a single event by id, including every corroborating article (source, url, timestamp).

入力スキーマ

{
  "type": "object",
  "properties": {
    "id": {
      "type": "integer",
      "description": "Event id from get_events"
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢search_articles(q, source, category, from, to, ...)

Search raw articles (not collapsed into events). Use when you want the underlying items or need per-outlet coverage rather than deduped happenings.

入力スキーマ

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free-text keyword on headline + summary"
    },
    "source": {
      "type": "string",
      "description": "Source slug"
    },
    "category": {
      "type": "string",
      "enum": [
        "crypto",
        "tradfi",
        "business",
        "tech",
        "politics",
        "world",
        "science",
        "health",
        "energy",
        "sports"
      ],
      "description": "Source category"
    },
    "from": {
      "type": "string",
      "description": "ISO 8601 date/time, e.g. 2026-07-01 or 2026-07-01T00:00:00Z"
    },
    "to": {
      "type": "string",
      "description": "ISO 8601 date/time, e.g. 2026-07-01 or 2026-07-01T00:00:00Z"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Max articles (default 25)"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_sources

List all news sources Newsflash tracks, with categories and live article counts.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢corpus_stats

Corpus size and freshness: source / article / event counts and the latest article timestamp.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

推奨プロンプト

search_research
Search for information about [topic] using newsflash
想定されるツール: search_articles
find_specific
Find [specific item] using newsflash
想定されるツール: search_articles
retrieve_data
Get details about [item] from newsflash
想定されるツール: get_events
fetch_info
Fetch [information type] using newsflash
想定されるツール: get_events
list_items
List all [items] available in newsflash
想定されるツール: list_sources

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 5 件
検証済みバージョンは記録されていませんツール 5 件
検証済みバージョンは記録されていませんツール 5 件