feat(docs): add .gitignore and enhance README with data source details

- Introduced a .gitignore file to exclude environment variables, logs, and temporary files.
- Updated README.md to reflect the new description and added a detailed table of 72+ data sources across 5 categories.
- Enhanced documentation in multiple languages (Japanese, Korean, Chinese) to include the new data source information.

.gitignore

@@ -0,0 +1,40 @@
+# Environment variables
+.env
+.env.local
+.env.*.local
+
+# API tokens
+*.token
+tokens/
+
+# Logs
+logs/
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
+# OS files
+.DS_Store
+Thumbs.db
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# Temporary files
+tmp/
+temp/
+*.tmp
+
+# Node modules (if using npm/yarn)
+node_modules/
+
+__pycache__
+
+# Build outputs
+dist/
+build/

README.md

@@ -1,6 +1,6 @@
 <p align="center">
   <b>OpenNews MCP Server</b><br>
-  Crypto News Aggregation · AI Ratings · Trading Signals · Real-time Updates
+  72+ Real-time Data Sources · 5 Engine Categories · AI Ratings · Trading Signals
 </p>
 
 <p align="center">
@@ -54,6 +54,20 @@ Steps:
 
 ---
 
+## Data Sources — 72+ Sources Across 5 Categories
+
+| Category | Count | Key Sources |
+|----------|-------|-------------|
+| **News** | 53 | Bloomberg, Reuters, Financial Times, CNBC, CNN, BBC, Fox Business, CoinDesk, Cointelegraph, The Block, Blockworks, Decrypt, DlNews, A16Z, TechCrunch, Wired, Politico, Business Insider, Twitter/X, Telegram, Weibo, Truth Social, U.S. Treasury, ECB, TASS, Handelsblatt, Welt, Ambrey, Morgan Stanley, PR Newswire, Coinbase, Phoenixnews, and more |
+| **Listing** | 9 | Binance, Coinbase, OKX, Bybit, Upbit, Bithumb, Robinhood, Hyperliquid, Aster |
+| **OnChain** | 3 | Hyperliquid Whale Trade, Hyperliquid Large Position, KOL Trade |
+| **Meme** | 1 | Twitter meme coin social sentiment |
+| **Market** | 6 | Price Change, Funding Rate, Funding Rate Difference, Large Liquidation, Market Trends, OI Change |
+
+All articles are **AI-analyzed** with impact score (0-100), trading signal (long/short/neutral), and bilingual summaries (EN/ZH).
+
+---
+
 ## What Can It Do?
 
 After connecting, just tell your AI assistant:
@@ -75,17 +89,17 @@ After connecting, just tell your AI assistant:
 
 | Category | Tool | Description |
 |----------|------|-------------|
-| Discovery | `get_news_sources` | Get all news source category tree |
-| | `list_news_types` | All available news source codes |
-| Search | `get_latest_news` | Latest articles |
-| | `search_news` | Keyword search |
-| | `search_news_by_coin` | By coin (BTC, ETH, SOL...) |
-| | `get_news_by_source` | By engine type and source |
-| | `get_news_by_engine` | By type (news, listing, onchain, meme, market) |
-| | `search_news_advanced` | Advanced search (multiple filters) |
-| AI | `get_high_score_news` | Articles with score >= threshold |
-| | `get_news_by_signal` | By signal: long / short / neutral |
-| Real-time | `subscribe_latest_news` | WebSocket real-time collection |
+| Discovery | `get_news_sources` | Full engine tree — all 5 categories and 72+ sources with metadata |
+| | `list_news_types` | Flat list of all source codes for filtering |
+| Search | `get_latest_news` | Latest articles across all 72+ sources |
+| | `search_news` | Full-text keyword search across all sources |
+| | `search_news_by_coin` | By coin (BTC, ETH, SOL...) across all sources |
+| | `get_news_by_source` | By specific source (e.g. engine_type="news", news_type="Bloomberg") |
+| | `get_news_by_engine` | By category: news, listing, onchain, meme, market |
+| | `search_news_advanced` | Multi-filter: coins + keywords + engine types combined |
+| AI | `get_high_score_news` | High AI impact score articles (0-100 scale) |
+| | `get_news_by_signal` | By AI trading signal: long / short / neutral |
+| Real-time | `subscribe_latest_news` | WebSocket live feed with coin & engine type filters |
 
 ---
 

docs/README_JA.md

@@ -1,6 +1,6 @@
 <p align="center">
   <b>OpenNews MCP Server</b><br>
-  暗号通貨ニュース集約 · AI 評価 · トレーディングシグナル · リアルタイム更新
+  72+ リアルタイムデータソース · 5 エンジンカテゴリ · AI 評価 · トレーディングシグナル
 </p>
 
 <p align="center">
@@ -54,6 +54,20 @@ opennews-mcp という MCP サーバーをレビューしてインストール
 
 ---
 
+## データソース — 5カテゴリ 72+ ソース
+
+| カテゴリ | 数量 | 主なソース |
+|---------|------|-----------|
+| **News** | 53 | Bloomberg、Reuters、Financial Times、CNBC、CNN、BBC、Fox Business、CoinDesk、Cointelegraph、The Block、Blockworks、Decrypt、DlNews、A16Z、TechCrunch、Wired、Politico、Business Insider、Twitter/X、Telegram、Weibo、Truth Social、U.S. Treasury、ECB、TASS、Handelsblatt、Welt、Ambrey、Morgan Stanley、PR Newswire、Coinbase、Phoenixnews など |
+| **Listing** | 9 | Binance、Coinbase、OKX、Bybit、Upbit、Bithumb、Robinhood、Hyperliquid、Aster |
+| **OnChain** | 3 | Hyperliquid Whale Trade、Hyperliquid Large Position、KOL Trade |
+| **Meme** | 1 | Twitter ミームコインソーシャルセンチメント |
+| **Market** | 6 | Price Change、Funding Rate、Funding Rate Difference、Large Liquidation、Market Trends、OI Change |
+
+すべての記事は **AI 分析済み** — 影響度スコア（0-100）、トレーディングシグナル（long/short/neutral）、中英バイリンガル要約付き。
+
+---
+
 ## 何ができる？
 
 接続後、AI アシスタントに話しかけるだけ：
@@ -75,17 +89,17 @@ opennews-mcp という MCP サーバーをレビューしてインストール
 
 | カテゴリ | ツール | 説明 |
 |---------|--------|------|
-| ディスカバリー | `get_news_sources` | 全ニュースソースカテゴリツリー |
-| | `list_news_types` | 利用可能なソースコード一覧 |
-| 検索 | `get_latest_news` | 最新記事 |
-| | `search_news` | キーワード検索 |
-| | `search_news_by_coin` | 通貨別（BTC, ETH, SOL...） |
-| | `get_news_by_source` | エンジンタイプとソース別 |
-| | `get_news_by_engine` | タイプ別（news, listing, onchain, meme, market） |
-| | `search_news_advanced` | 高度な検索（複数フィルタ） |
-| AI | `get_high_score_news` | スコア >= 閾値の記事 |
-| | `get_news_by_signal` | シグナル別：long / short / neutral |
-| リアルタイム | `subscribe_latest_news` | WebSocket リアルタイム収集 |
+| ディスカバリー | `get_news_sources` | 完全エンジンツリー — 5カテゴリ 72+ ソースとメタデータ |
+| | `list_news_types` | フィルタ用ソースコードのフラットリスト |
+| 検索 | `get_latest_news` | 72+ ソースから最新記事を取得 |
+| | `search_news` | 全ソース横断キーワード検索 |
+| | `search_news_by_coin` | 通貨別（BTC, ETH, SOL...）全ソース横断 |
+| | `get_news_by_source` | 特定ソース指定（例：engine_type="news", news_type="Bloomberg"） |
+| | `get_news_by_engine` | カテゴリ別：news, listing, onchain, meme, market |
+| | `search_news_advanced` | 複合フィルタ：通貨 + キーワード + エンジンタイプ |
+| AI | `get_high_score_news` | 高 AI 影響度スコア記事（0-100 スケール） |
+| | `get_news_by_signal` | AI トレーディングシグナル別：long / short / neutral |
+| リアルタイム | `subscribe_latest_news` | WebSocket ライブフィード、通貨・エンジンタイプフィルタ対応 |
 
 ---
 

docs/README_KO.md

@@ -1,6 +1,6 @@
 <p align="center">
   <b>OpenNews MCP Server</b><br>
-  암호화폐 뉴스 집계 · AI 평가 · 트레이딩 시그널 · 실시간 업데이트
+  72+ 실시간 데이터 소스 · 5개 엔진 카테고리 · AI 평가 · 트레이딩 시그널
 </p>
 
 <p align="center">
@@ -54,6 +54,20 @@ opennews-mcp MCP 서버를 검토하고 설치해주세요. 프로젝트는 로
 
 ---
 
+## 데이터 소스 — 5개 카테고리 72+ 소스
+
+| 카테고리 | 수량 | 주요 소스 |
+|---------|------|----------|
+| **News** | 53 | Bloomberg, Reuters, Financial Times, CNBC, CNN, BBC, Fox Business, CoinDesk, Cointelegraph, The Block, Blockworks, Decrypt, DlNews, A16Z, TechCrunch, Wired, Politico, Business Insider, Twitter/X, Telegram, Weibo, Truth Social, U.S. Treasury, ECB, TASS, Handelsblatt, Welt, Ambrey, Morgan Stanley, PR Newswire, Coinbase, Phoenixnews 등 |
+| **Listing** | 9 | Binance, Coinbase, OKX, Bybit, Upbit, Bithumb, Robinhood, Hyperliquid, Aster |
+| **OnChain** | 3 | Hyperliquid Whale Trade, Hyperliquid Large Position, KOL Trade |
+| **Meme** | 1 | Twitter 밈코인 소셜 센티먼트 |
+| **Market** | 6 | Price Change, Funding Rate, Funding Rate Difference, Large Liquidation, Market Trends, OI Change |
+
+모든 기사는 **AI 분석** 완료 — 영향도 점수(0-100), 트레이딩 시그널(long/short/neutral), 중영 이중 언어 요약 포함.
+
+---
+
 ## 무엇을 할 수 있나요?
 
 연결 후 AI 어시스턴트에게 말하기만 하면 됩니다:
@@ -75,17 +89,17 @@ opennews-mcp MCP 서버를 검토하고 설치해주세요. 프로젝트는 로
 
 | 카테고리 | 도구 | 설명 |
 |---------|------|------|
-| 디스커버리 | `get_news_sources` | 전체 뉴스 소스 카테고리 트리 |
-| | `list_news_types` | 사용 가능한 소스 코드 목록 |
-| 검색 | `get_latest_news` | 최신 기사 |
-| | `search_news` | 키워드 검색 |
-| | `search_news_by_coin` | 코인별 (BTC, ETH, SOL...) |
-| | `get_news_by_source` | 엔진 유형과 소스별 |
-| | `get_news_by_engine` | 유형별 (news, listing, onchain, meme, market) |
-| | `search_news_advanced` | 고급 검색 (다중 필터) |
-| AI | `get_high_score_news` | 점수 >= 임계값 기사 |
-| | `get_news_by_signal` | 시그널별: long / short / neutral |
-| 실시간 | `subscribe_latest_news` | WebSocket 실시간 수집 |
+| 디스커버리 | `get_news_sources` | 완전한 엔진 트리 — 5개 카테고리 72+ 소스 및 메타데이터 |
+| | `list_news_types` | 필터용 소스 코드 플랫 리스트 |
+| 검색 | `get_latest_news` | 72+ 소스에서 최신 기사 조회 |
+| | `search_news` | 전체 소스 대상 키워드 검색 |
+| | `search_news_by_coin` | 코인별 (BTC, ETH, SOL...) 전체 소스 대상 |
+| | `get_news_by_source` | 특정 소스 지정 (예: engine_type="news", news_type="Bloomberg") |
+| | `get_news_by_engine` | 카테고리별: news, listing, onchain, meme, market |
+| | `search_news_advanced` | 복합 필터: 코인 + 키워드 + 엔진 유형 조합 |
+| AI | `get_high_score_news` | 높은 AI 영향도 점수 기사 (0-100 스케일) |
+| | `get_news_by_signal` | AI 트레이딩 시그널별: long / short / neutral |
+| 실시간 | `subscribe_latest_news` | WebSocket 라이브 피드, 코인 및 엔진 유형 필터 지원 |
 
 ---
 

docs/README_ZH.md

@@ -1,6 +1,6 @@
 <p align="center">
   <b>OpenNews MCP Server</b><br>
-  加密货币新闻聚合 · AI 评分 · 交易信号 · 实时更新
+  72+ 实时数据源 · 5 大引擎类别 · AI 评分 · 交易信号
 </p>
 
 <p align="center">
@@ -54,6 +54,20 @@ cp -r openclaw-skill/opennews ~/.openclaw/skills/
 
 ---
 
+## 数据源 — 5 大类别 72+ 数据源
+
+| 类别 | 数量 | 主要来源 |
+|------|------|----------|
+| **News** | 53 | Bloomberg、Reuters、Financial Times、CNBC、CNN、BBC、Fox Business、CoinDesk、Cointelegraph、The Block、Blockworks、Decrypt、DlNews、A16Z、TechCrunch、Wired、Politico、Business Insider、Twitter/X、Telegram、Weibo、Truth Social、U.S. Treasury、ECB、TASS、Handelsblatt、Welt、Ambrey、Morgan Stanley、PR Newswire、Coinbase、凤凰新闻等 |
+| **Listing** | 9 | Binance、Coinbase、OKX、Bybit、Upbit、Bithumb、Robinhood、Hyperliquid、Aster |
+| **OnChain** | 3 | Hyperliquid Whale Trade、Hyperliquid Large Position、KOL Trade |
+| **Meme** | 1 | Twitter meme 币社交情绪 |
+| **Market** | 6 | Price Change、Funding Rate、Funding Rate Difference、Large Liquidation、Market Trends、OI Change |
+
+所有文章均经 **AI 分析**，包含影响力评分（0-100）、交易信号（long/short/neutral）及中英双语摘要。
+
+---
+
 ## 功能介绍
 
 连接后，直接告诉你的 AI 助手：
@@ -75,17 +89,17 @@ cp -r openclaw-skill/opennews ~/.openclaw/skills/
 
 | 分类 | 工具 | 描述 |
 |------|------|------|
-| 发现 | `get_news_sources` | 获取所有新闻来源分类树 |
-| | `list_news_types` | 所有可用的新闻来源代码 |
-| 搜索 | `get_latest_news` | 最新文章 |
-| | `search_news` | 关键词搜索 |
-| | `search_news_by_coin` | 按币种搜索 (BTC, ETH, SOL...) |
-| | `get_news_by_source` | 按引擎类型和来源搜索 |
-| | `get_news_by_engine` | 按类型搜索 (news, listing, onchain, meme, market) |
-| | `search_news_advanced` | 高级搜索（多条件筛选） |
-| AI | `get_high_score_news` | 评分 >= 阈值的文章 |
-| | `get_news_by_signal` | 按信号搜索: long / short / neutral |
-| 实时 | `subscribe_latest_news` | WebSocket 实时采集 |
+| 发现 | `get_news_sources` | 完整引擎树 — 5 大类别 72+ 数据源及元数据 |
+| | `list_news_types` | 所有来源代码的扁平列表，用于过滤 |
+| 搜索 | `get_latest_news` | 跨 72+ 数据源获取最新文章 |
+| | `search_news` | 跨所有数据源全文关键词搜索 |
+| | `search_news_by_coin` | 按币种搜索 (BTC, ETH, SOL...) 跨所有数据源 |
+| | `get_news_by_source` | 按特定来源搜索 (如 engine_type="news", news_type="Bloomberg") |
+| | `get_news_by_engine` | 按类别搜索: news, listing, onchain, meme, market |
+| | `search_news_advanced` | 多条件组合: 币种 + 关键词 + 引擎类型 |
+| AI | `get_high_score_news` | 高 AI 影响力评分文章 (0-100 分制) |
+| | `get_news_by_signal` | 按 AI 交易信号: long / short / neutral |
+| 实时 | `subscribe_latest_news` | WebSocket 实时推送，支持币种和引擎类型过滤 |
 
 ---
 

knowledge/guide.md

@@ -2,46 +2,159 @@
 
 ## Overview
 
-This MCP server provides access to crypto news from the 6551 news platform
-via REST API and WebSocket. It replaces direct database access with API calls.
+This MCP server provides real-time access to a **massive, multi-source crypto & financial news aggregation platform** powered by 6551.io. It aggregates **72+ data sources** across 5 engine categories, covering everything from Bloomberg and Reuters breaking news to on-chain whale trades, meme coin signals, and market anomaly alerts — all with AI-powered ratings and trading signal analysis.
+
+## Data Source Coverage (5 Categories, 72+ Sources)
+
+### 1. News — 53 sources (engineType: "news")
+Premium financial & crypto media, government agencies, social platforms:
+
+| Source Code | Description |
+|-------------|-------------|
+| 6551News | 6551 platform original analysis |
+| BWEnews | BWE news wire |
+| Bloomberg | Bloomberg — top-tier financial news |
+| Reuters | Reuters — global wire service |
+| A16Z | a16z (Andreessen Horowitz) — leading crypto VC |
+| AGGRNEWS | Aggregated news feed |
+| dbnews | DB news |
+| Tree | Tree news |
+| Velo | Velo data intelligence |
+| Phoenixnews | Phoenix news (凤凰新闻) |
+| BBC | BBC — British Broadcasting Corporation |
+| Binance | Binance announcements & blog |
+| Blockworks | Blockworks — crypto-native media |
+| Business Insider | Business Insider |
+| Chainwire | Chainwire — crypto press releases |
+| CNBC | CNBC — financial television |
+| CNN | CNN — US news network |
+| CoinDesk | CoinDesk — leading crypto media |
+| Cointelegraph | Cointelegraph — crypto media |
+| Crypto Narratives | Crypto narrative tracking |
+| Decrypt | Decrypt — crypto & web3 media |
+| DlNews | DL News — crypto investigative journalism |
+| Financial Times | Financial Times — premium business news |
+| Interfax | Interfax — Russian news agency |
+| Medium | Medium blog posts |
+| MS NOW | Morgan Stanley NOW — institutional research |
+| Politico | Politico — US & EU political news |
+| PR Newswire | PR Newswire — press releases |
+| TechCrunch | TechCrunch — tech & startup news |
+| Techinasia | Tech in Asia — Asian tech news |
+| Telegram | Telegram channels |
+| Telegraph | The Telegraph — UK news |
+| The Big Whale | The Big Whale — European crypto media |
+| The Block | The Block — crypto data & journalism |
+| The Verge | The Verge — tech media |
+| Token Relations | Token relations & partnerships |
+| U.S. Treasury | U.S. Treasury Department — official statements |
+| Truth Social | Truth Social — Trump's social platform |
+| Twitter/X | Twitter/X posts from crypto influencers |
+| X / Twitter Profile | Twitter/X profile changes (name, bio updates) |
+| U.S. Trade Representative | USTR — trade policy announcements |
+| Weibo | Weibo (微博) — Chinese social media |
+| Wired | Wired magazine — tech journalism |
+| Coinbase | Coinbase announcements & blog |
+| Crypto in America | Crypto in America coverage |
+| AI_Helper | AI-generated analysis & helper |
+| Fox Business | Fox Business — US financial news |
+| TASS | TASS — Russian state news agency |
+| Hadelsblatt | Hadelsblatt — German business |
+| Welt | Welt — German newspaper |
+| Handelsblatt | Handelsblatt — German business newspaper |
+| Ambrey | Ambrey — maritime & geopolitical intelligence |
+| ECB | European Central Bank — official communications |
+
+### 2. Listing — 9 sources (engineType: "listing")
+Token listing announcements from major exchanges:
+
+| Source Code | Description |
+|-------------|-------------|
+| Binance | Binance new token listings |
+| Aster | Aster exchange listings |
+| Hyperliquid | Hyperliquid perp listings |
+| Bithumb | Bithumb (Korean exchange) listings |
+| Upbit | Upbit (Korean exchange) listings |
+| Robinhood | Robinhood crypto listings |
+| Bybit | Bybit new token listings |
+| OKX | OKX new token listings |
+| Coinbase | Coinbase new token listings |
+
+### 3. OnChain — 3 sources (engineType: "onchain")
+On-chain activity from whales and key opinion leaders:
+
+| Source Code | Description |
+|-------------|-------------|
+| Hyperliquid Whale Trade | Hyperliquid whale trade alerts |
+| Hyperliquid Large Position | Hyperliquid large position changes |
+| KOL Trade | KOL (Key Opinion Leader) on-chain trades |
+
+### 4. Meme — 1 source (engineType: "meme")
+Meme coin social sentiment tracking:
+
+| Source Code | Description |
+|-------------|-------------|
+| Twitter | Twitter/X meme coin discussions & viral posts |
+
+### 5. Market — 6 sources (engineType: "market")
+Market anomaly detection and quantitative signals:
+
+| Source Code | Description |
+|-------------|-------------|
+| Price Change | Significant price movements (pumps/dumps) |
+| Funding Rate | Funding rate anomalies (perp futures) |
+| Funding Rate Difference | Cross-exchange funding rate divergences |
+| Large Liquidation | Large liquidation events |
+| Market Trends | Overall market trend shifts |
+| OI Change | Open interest significant changes |
 
 ## Available Tools
 
 ### Discovery
-- **get_news_sources**: Get all available news source categories (Bloomberg, Reuters, etc.)
-- **list_news_types**: Flat list of news type codes for filtering
+- **get_news_sources**: Get the full engine tree with all 5 categories and 72+ sources, including metadata (names, icons, AI-enabled status)
+- **list_news_types**: Flat list of all source codes for use in filters
 
 ### News Search
-- **get_latest_news**: Get most recent news (no filters)
-- **search_news**: Search by keyword
-- **search_news_by_coin**: Search by coin symbol (BTC, ETH, SOL, etc.)
-- **get_news_by_source**: Filter by source (Bloomberg, Reuters, Coindesk, etc.)
-- **get_news_by_engine**: Filter by engine type (news, listing, onchain, meme, market)
-- **search_news_by_date**: Search within a date range
+- **get_latest_news**: Most recent articles across all sources
+- **search_news**: Full-text keyword search across all sources
+- **search_news_by_coin**: Filter by coin symbol (BTC, ETH, SOL, etc.)
+- **get_news_by_source**: Filter by specific source within a category (e.g. engine_type="news", news_type="Bloomberg")
+- **get_news_by_engine**: Filter by entire engine category (e.g. "listing" for all exchange listing alerts)
+- **search_news_advanced**: Combined multi-filter search (coins + keywords + engine types + has_coin)
 
-### AI Ratings
-- **get_high_score_news**: Get articles with high AI scores (>=70)
-- **get_news_by_signal**: Filter by trading signal (long/short/neutral)
+### AI Ratings & Signals
+- **get_high_score_news**: Articles with high AI impact scores (0-100 scale)
+- **get_news_by_signal**: Filter by AI trading signal — "long" (bullish), "short" (bearish), or "neutral"
 
 ### Real-time
-- **subscribe_latest_news**: Connect to WebSocket for live news updates
+- **subscribe_latest_news**: WebSocket live feed with optional filters by coins, engine types
 
 ## Workflow Examples
 
-1. **Quick market overview**: `get_latest_news(limit=10)`
-2. **Coin-specific research**: `search_news_by_coin(coin="BTC", limit=20)`
-3. **Source-specific feed**: `get_news_by_source(source="Bloomberg")`
-4. **Bullish signals**: `get_news_by_signal(signal="long")`
-5. **High-impact news**: `get_high_score_news(min_score=80)`
+1. **Breaking news scan**: `get_latest_news(limit=20)` — see what's happening right now across all 72+ sources
+2. **Institutional media only**: `get_news_by_source(engine_type="news", news_type="Bloomberg")` — Bloomberg-only feed
+3. **Exchange listing alpha**: `get_news_by_engine(engine_type="listing")` — catch new token listings on Binance, Coinbase, Upbit, etc.
+4. **Whale watching**: `get_news_by_engine(engine_type="onchain")` — Hyperliquid whale trades & KOL activity
+5. **Market anomalies**: `get_news_by_engine(engine_type="market")` — price spikes, liquidations, OI changes, funding rate divergences
+6. **Coin deep-dive**: `search_news_by_coin(coin="ETH", limit=30)` — all ETH-related news across every source
+7. **Bullish signals**: `get_news_by_signal(signal="long")` — AI-detected bullish catalysts
+8. **Multi-filter power search**: `search_news_advanced(coins="BTC,ETH", engine_types="news:Bloomberg,Reuters;market:", keyword="ETF")` — Bloomberg & Reuters ETF news for BTC/ETH plus all market signals
+9. **Live monitoring**: `subscribe_latest_news(wait_seconds=15, coins="BTC", engine_types="news:;market:")` — real-time BTC news + market anomalies
 
 ## Data Structure
 
 Each news article contains:
 - `id`: Unique article ID
 - `text`: Article headline/content
-- `newsType`: Source type (Bloomberg, Reuters, etc.)
-- `engineType`: Engine category (news, listing, onchain, etc.)
+- `newsType`: Source code (e.g. "Bloomberg", "Binance", "price_change")
+- `engineType`: Engine category ("news", "listing", "onchain", "meme", "market")
 - `link`: URL to original article
-- `coins`: Array of related coins with symbol, market_type, match
-- `aiRating`: AI analysis with score, grade, signal, summary, enSummary
-- `ts`: Timestamp of the article
+- `coins`: Array of related coins `[{symbol, market_type, match}]`
+- `aiRating`: AI analysis object:
+  - `score`: Impact score 0-100
+  - `grade`: Letter grade (A/B/C/D)
+  - `signal`: Trading signal ("long" / "short" / "neutral")
+  - `status`: Analysis status ("done" = completed)
+  - `summary`: Chinese summary
+  - `enSummary`: English summary
+- `ts`: ISO timestamp

openclaw-skill/opennews/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: opennews
-description: Crypto news search, AI ratings, trading signals, and real-time updates via the OpenNews 6551 API. Supports keyword search, coin filtering, source filtering, AI score ranking, and WebSocket live feeds.
+description: "Real-time crypto & financial news aggregator — 72+ data sources across 5 categories (News: Bloomberg, Reuters, FT, CNBC, CoinDesk, Twitter/X + 47 more; Listing: Binance, Coinbase, OKX + 6 more; OnChain: whale & KOL trades; Meme: social sentiment; Market: price/funding/liquidation alerts). AI-analyzed with impact score, trading signals, and bilingual summaries."
 
 user-invocable: true
 metadata:
@@ -26,12 +26,22 @@ metadata:
 
 # OpenNews Crypto News Skill
 
-Query crypto news from the 6551 platform REST API. All endpoints require a Bearer token via `$OPENNEWS_TOKEN`.
+Real-time crypto & financial news aggregator powered by 6551.io — **72+ data sources** across 5 engine categories, all AI-analyzed with impact scores, trading signals, and bilingual summaries.
 
 **Get your token**: https://6551.io/mcp
 
 **Base URL**: `https://ai.6551.io`
 
+## Data Sources — 72+ Sources Across 5 Categories
+
+| Category | Count | Key Sources |
+|----------|-------|-------------|
+| **News** | 53 | Bloomberg, Reuters, Financial Times, CNBC, CNN, BBC, Fox Business, CoinDesk, Cointelegraph, The Block, Blockworks, Decrypt, DlNews, A16Z, TechCrunch, Wired, Politico, Business Insider, Twitter/X, Telegram, Weibo, Truth Social, U.S. Treasury, ECB, TASS, Handelsblatt, Welt, Ambrey, Morgan Stanley, PR Newswire, Coinbase, Phoenixnews, and more |
+| **Listing** | 9 | Binance, Coinbase, OKX, Bybit, Upbit, Bithumb, Robinhood, Hyperliquid, Aster |
+| **OnChain** | 3 | Hyperliquid Whale Trade, Hyperliquid Large Position, KOL Trade |
+| **Meme** | 1 | Twitter meme coin social sentiment |
+| **Market** | 6 | Price Change, Funding Rate, Funding Rate Difference, Large Liquidation, Market Trends, OI Change |
+
 ## Authentication
 
 All requests require the header:
@@ -45,14 +55,14 @@ Authorization: Bearer $OPENNEWS_TOKEN
 
 ### 1. Get News Sources
 
-Fetch all available news source categories organized by engine type.
+Fetch the full engine tree with all 5 categories and 72+ sources.
 
 ```bash
 curl -s -H "Authorization: Bearer $OPENNEWS_TOKEN" \
   "https://ai.6551.io/open/news_type"
 ```
 
-Returns a tree with engine types (`news`, `listing`, `onchain`, `meme`, `market`) and their sub-categories.
+Returns a tree with engine types (`news` — 53 sources, `listing` — 9 exchanges, `onchain` — 3 whale/KOL trackers, `meme` — 1 sentiment source, `market` — 6 anomaly signals) and their sub-categories.
 
 ### 2. Search News
 
@@ -71,7 +81,7 @@ curl -s -X POST "https://ai.6551.io/open/news_search" \
 curl -s -X POST "https://ai.6551.io/open/news_search" \
   -H "Authorization: Bearer $OPENNEWS_TOKEN" \
   -H "Content-Type: application/json" \
-  -d '{"q": "bitcoin ETF", "limit": 10, "page": 1}'
+  -d '{"q": "bitcoin OR ETF", "limit": 10, "page": 1}'
 ```
 
 **Search by coin symbol:**
@@ -109,6 +119,8 @@ curl -s -X POST "https://ai.6551.io/open/news_search" \
 | `engineTypes`| map[string][]string       | no       | Filter by engine and news types               |
 | `hasCoin`    | boolean                   | no       | Only return news with associated coins        |
 
+Important: You need to understand the user's query intent and perform word segmentation, then combine them using OR/AND to form search keywords, supporting both Chinese and English.
+
 ---
 
 ## Data Structures

openclaw-skill/opennews/package.json

@@ -1,7 +1,7 @@
 {
   "name": "opennews",
   "version": "0.1.0",
-  "description": "Crypto news search, AI ratings, trading signals, and real-time updates via the OpenNews 6551 API",
+  "description": "72+ real-time crypto & financial news sources across 5 categories (News, Listing, OnChain, Meme, Market) with AI ratings, trading signals, and bilingual summaries via the OpenNews 6551 API",
   "author": "0xfaskety",
   "license": "MIT",
   "homepage": "https://github.com/0xfaskety/opennews-mcp",
@@ -22,6 +22,14 @@
     "ai-ratings",
     "signals",
     "blockchain",
-    "defi"
+    "defi",
+    "bloomberg",
+    "reuters",
+    "onchain",
+    "whale-tracking",
+    "market-signals",
+    "exchange-listings",
+    "meme-coins",
+    "real-time"
   ]
 }

src/opennews_mcp/app.py

@@ -33,8 +33,29 @@ async def app_lifespan(server: FastMCP) -> AsyncIterator[AppContext]:
 
 
 # ---------- FastMCP instance ----------
+_INSTRUCTIONS = """\
+OpenNews MCP — Real-time crypto & financial news aggregator powered by 6551.io.
+
+Aggregates 72+ data sources across 5 engine categories:
+- NEWS (53 sources): Bloomberg, Reuters, Financial Times, CNBC, CNN, BBC, Fox Business, \
+CoinDesk, Cointelegraph, The Block, Blockworks, Decrypt, DlNews, A16Z, TechCrunch, Wired, \
+Politico, Business Insider, Twitter/X, Telegram, Weibo, Truth Social, U.S. Treasury, ECB, \
+TASS, Handelsblatt, Welt, Ambrey, Morgan Stanley, PR Newswire, Coinbase, Phoenixnews, and more.
+- LISTING (9 sources): Binance, Coinbase, OKX, Bybit, Upbit, Bithumb, Robinhood, \
+Hyperliquid, Aster — new token listing announcements.
+- ONCHAIN (3 sources): Hyperliquid Whale Trade, Hyperliquid Large Position, \
+KOL Trade — on-chain whale & KOL activity.
+- MEME (1 source): Twitter meme coin social sentiment.
+- MARKET (6 sources): Price Change, Funding Rate, Funding Rate Difference, \
+Large Liquidation, Market Trends, OI Change — quantitative market signals.
+
+All articles are AI-analyzed with impact score (0-100), trading signal (long/short/neutral), \
+and bilingual summaries (EN/ZH).
+"""
+
 mcp = FastMCP(
     "opennews-6551",
+    instructions=_INSTRUCTIONS,
     lifespan=app_lifespan,
     json_response=True,
 )

src/opennews_mcp/tools/discovery.py

@@ -9,10 +9,27 @@ from opennews_mcp.app import mcp
 async def get_news_sources(ctx: Context) -> dict:
     """Get all available news source categories and their metadata.
 
-    Returns a tree structure with engine types (news, listing, onchain, meme, market)
-    and their sub-categories (Bloomberg, Reuters, Binance, etc.).
+    This platform aggregates 72+ real-time data sources across 5 engine categories:
 
-    Use this first to understand what news sources are available before searching.
+    NEWS (53 sources): Bloomberg, Reuters, Financial Times, CNBC, CNN, BBC, Fox Business,
+      CoinDesk, Cointelegraph, The Block, Blockworks, Decrypt, DlNews, A16Z, TechCrunch,
+      Wired, Politico, Business Insider, Twitter/X, Telegram, Weibo, Truth Social,
+      U.S. Treasury, ECB, TASS, Handelsblatt, Welt, Ambrey, Morgan Stanley (MS NOW),
+      PR Newswire, Coinbase, Phoenixnews, and more.
+
+    LISTING (9 sources): Binance, Coinbase, OKX, Bybit, Upbit, Bithumb, Robinhood,
+      Hyperliquid, Aster — new token listing announcements from major exchanges.
+
+    ONCHAIN (3 sources): Hyperliquid Whale Trade, Hyperliquid Large Position,
+      KOL Trade — on-chain whale & KOL activity alerts.
+
+    MEME (1 source): Twitter — meme coin social sentiment tracking.
+
+    MARKET (6 sources): Price Change, Funding Rate, Funding Rate Difference,
+      Large Liquidation, Market Trends, OI Change — quantitative market anomaly signals.
+
+    Returns a tree structure with all engine types and their sub-categories.
+    Use this first to discover what sources are available before searching.
     """
     api = ctx.request_context.lifespan_context.api
 
@@ -55,6 +72,7 @@ async def list_news_types(ctx: Context) -> dict:
     Returns a flat list of news source codes that can be used with
     the newsType parameter in search_news.
     """
+    # See get_news_sources for the full 72+ source catalog.
     api = ctx.request_context.lifespan_context.api
 
     try:

src/opennews_mcp/tools/news.py

@@ -1,7 +1,8 @@
-"""News content tools — search and retrieve crypto news via REST API.
+"""News content tools — search and retrieve news from 72+ sources via REST API.
 
+Covers 5 engine categories: news (53 premium media & social sources), listing (9 exchanges),
+onchain (whale & KOL trades), meme (social sentiment), market (6 anomaly signals).
 Uses POST /open/news_search as the primary data source.
-Returns raw article data as-is from the API.
 """
 
 from mcp.server.fastmcp import Context
@@ -14,7 +15,8 @@ from opennews_mcp.config import clamp_limit, make_serializable, MAX_ROWS
 async def get_latest_news(ctx: Context, limit: int = 10) -> dict:
     """Get the most recent crypto news articles, newest first.
 
-    Returns news with title text, source, link, related coins, AI rating, and tags.
+    Returns news from 72+ sources across all 5 categories (news, listing, onchain,
+    meme, market) with title text, source, link, related coins, AI rating, and tags.
 
     Args:
         limit: Maximum number of articles to return (default 10, max 100).
@@ -36,6 +38,9 @@ async def get_latest_news(ctx: Context, limit: int = 10) -> dict:
 async def search_news(keyword: str, ctx: Context, limit: int = 10) -> dict:
     """Search crypto news by keyword in text content.
 
+    Searches across all 72+ sources including Bloomberg, Reuters, CoinDesk,
+    Twitter/X, on-chain alerts, exchange listings, and market signals.
+
     Args:
         keyword: Search term (e.g. "bitcoin", "SEC", "ETF").
         limit: Maximum results (default 10, max 100).
@@ -57,6 +62,9 @@ async def search_news(keyword: str, ctx: Context, limit: int = 10) -> dict:
 async def search_news_by_coin(coin: str, ctx: Context, limit: int = 10) -> dict:
     """Search news related to a specific cryptocurrency coin/token.
 
+    Finds all mentions across 72+ sources: media coverage, exchange listings,
+    whale trades, meme sentiment, and market anomalies for the given coin.
+
     Args:
         coin: Coin symbol or name (e.g. "BTC", "ETH", "SOL", "TRUMP").
         limit: Maximum results (default 10, max 100).
@@ -83,6 +91,12 @@ async def get_news_by_source(engine_type: str, news_type: str, ctx: Context, lim
     Args:
         engine_type: The engine type (e.g. "news", "listing", "onchain", "meme", "market").
         news_type: The news source code (e.g. "Bloomberg", "Reuters", "Coindesk").
+            For listing: "Binance", "Coinbase", "OKX", "Bybit", "Upbit", "Bithumb",
+              "Robinhood", "Hyperliquid", "Aster".
+            For onchain: "Hyperliquid Whale Trade", "Hyperliquid Large Position", "KOL Trade".
+            For meme: "Twitter".
+            For market: "Price Change", "Funding Rate", "Funding Rate Difference",
+              "Large Liquidation", "Market Trends", "OI Change".
         limit: Maximum results (default 10, max 100).
     """
     api = ctx.request_context.lifespan_context.api
@@ -103,6 +117,11 @@ async def get_news_by_engine(engine_type: str, ctx: Context, limit: int = 10) ->
     """Get news articles filtered by engine type.
 
     Engine types: "news", "listing", "onchain", "meme", "market".
+      - "news": 53 sources — Bloomberg, Reuters, FT, CNBC, CNN, BBC, CoinDesk, Twitter/X, etc.
+      - "listing": 9 exchanges — Binance, Coinbase, OKX, Bybit, Upbit, Bithumb, Robinhood, etc.
+      - "onchain": Whale trades & KOL activity on Hyperliquid.
+      - "meme": Meme coin social sentiment from Twitter.
+      - "market": Price changes, funding rates, liquidations, OI changes, market trends.
 
     Args:
         engine_type: The engine type code.
@@ -132,6 +151,9 @@ async def search_news_advanced(
 ) -> dict:
     """Advanced news search with multiple filters.
 
+    Combines coin, keyword, engine type, and source filters for precise queries
+    across the full 72+ source catalog.
+
     Args:
         coins: Comma-separated coin symbols (e.g. "BTC,ETH").
         keyword: Optional search keyword.
@@ -174,6 +196,9 @@ async def search_news_advanced(
 async def get_high_score_news(ctx: Context, min_score: int = 70, limit: int = 10) -> dict:
     """Get highly-rated news articles (by AI score), sorted by score descending.
 
+    AI scores range 0-100 and reflect potential market impact.
+    All articles from 72+ sources are AI-analyzed with score, grade, signal, and summary.
+
     Args:
         min_score: Minimum score threshold (default 70).
         limit: Maximum results to return (default 10, max 100).
@@ -204,6 +229,8 @@ async def get_high_score_news(ctx: Context, min_score: int = 70, limit: int = 10
 async def get_news_by_signal(signal: str, ctx: Context, limit: int = 10) -> dict:
     """Get news filtered by trading signal type.
 
+    Each article from 72+ sources is AI-analyzed for trading direction.
+
     Args:
         signal: The signal type: "long" (bullish), "short" (bearish), or "neutral".
         limit: Maximum results (default 10, max 100).

src/opennews_mcp/tools/realtime.py

@@ -1,4 +1,4 @@
-"""Real-time news tools — WebSocket subscription for live news updates."""
+"""Real-time news tools — WebSocket subscription for live updates from 72+ sources."""
 
 from mcp.server.fastmcp import Context
 
@@ -20,6 +20,10 @@ async def subscribe_latest_news(
     Connects to the WebSocket feed, subscribes to news with optional filters,
     and collects incoming messages for the specified duration.
 
+    Streams live data from 72+ sources across 5 categories:
+    news (Bloomberg, Reuters, etc.), listing (Binance, Coinbase, etc.),
+    onchain (whale trades), meme (Twitter sentiment), market (price/funding/liquidation alerts).
+
     Args:
         wait_seconds: How long to listen for news (default 10, max 30 seconds).
         max_items: Maximum news items to collect (default 5, max 20).