Skills Plugins MCP Prompt Model 博客 我的中心
Data & Consulting #data #trading #ai

opennews

Real-time crypto, equities, macro, and financial market news aggregator — 85+ data sources across 6 categories covering digital assets, U.S. stocks, semiconductors, AI infrastructure, supply chains, commodities, rates, policy, and market-moving social/news signals. Sources include Bloomberg, Reuters, FT, CNBC, CoinDesk, Twitter/X, Binance, Coinbase, OKX, Hyperliquid whale trades, price/funding/liquidation alerts, and 12 AI prediction signals. AI-analyzed with impact score, trading signals, and bilingual summaries. **Free tools available without token**.

DeepseekModel Curated skill Quality Excellent · 90 v1.0.0

Get

https://deepseekmodel.com/api/download.php?id=6551team-opennews-mcp-openclaw-skill-opennews-skill-md&format=skill
Download .skill Standard format with system_prompt and model_config, ready for any agent framework
The actual content of the system_prompt field in the .skill file.
name opennews description Real-time crypto, equities, macro, and financial market news aggregator — 85+ data sources across 6 categories covering digital assets, U.S. stocks, semiconductors, AI infrastructure, supply chains, commodities, rates, policy, and market-moving social/news signals. Sources include Bloomberg, Reuters, FT, CNBC, CoinDesk, Twitter/X, Binance, Coinbase, OKX, Hyperliquid whale trades, price/funding/liquidation alerts, and 12 AI prediction signals. AI-analyzed with impact score, trading signals, and bilingual summaries. **Free tools available without token**. user-invocable true metadata {"openclaw":{"requires":{"bins":"[Truncated]"},"optionalEnv":["OPENNEWS_TOKEN"],"primaryEnv":"OPENNEWS_TOKEN","emoji":"📰","install":["[Truncated]"],"os":["darwin","linux","win32"]},"version":"1.0.7"} OpenNews Financial Market News Skill Real-time crypto, equities, macro, and financial market news aggregator powered by 6551.io — 85+ data sources across 6 engine categories, all AI-analyzed with impact scores, trading signals, and bilingual summaries. Use OpenNews for time-sensitive, market-moving news and signals across digital assets, U.S. stocks, semiconductors, AI infrastructure, supply chains, commodities, rates, policy, and social/news channels that can affect prices or investor positioning. Get your token : https://6551.io/mcp Base URL : https://ai.6551.io Data Sources — 85+ Sources Across 6 Categories Category Count Key Sources News 55 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, GlobeNewswire, Business Wire, Coinbase, and more; useful for crypto, U.S. equities, semiconductors, AI infrastructure, supply chains, commodities, rates, policy, and market-moving social/news signals Listing 9 Binance, Coinbase, OKX, Bybit, Upbit, Bithumb, Robinhood, Hyperliquid, Aster OnChain 2 Hyperliquid Whale Trade, Hyperliquid Large Position Meme 1 Twitter meme coin social sentiment Market 6 Price Change, Funding Rate, Funding Rate Difference, Large Liquidation, Market Trends, OI Change Prediction 12 CORRELATION_LOGICAL, SMART_MONEY_TRADE, PRICE_SPIKE, CLUSTER_ENTRY, WHALE_POSITION, NEW_WALLET_TRADE, INSIDER_PATTERN, CORRELATION_NARRATIVE, CORRELATION_HEDGE, CORRELATION_ENTITY_GEO, CORRELATION_CAUSAL, SETTLEMENT_ARBITRAGE Authentication All requests require the header: Authorization: Bearer $OPENNEWS_TOKEN News Operations 1. Get News Sources Fetch the full engine tree with all 6 categories and 85+ sources. curl -s -H "Authorization: Bearer $OPENNEWS_TOKEN " \ "https://ai.6551.io/open/news_type" Returns a tree with engine types ( news — 55 sources, listing — 9 exchanges, onchain — 2 Hyperliquid trackers, meme — 1 sentiment source, market — 6 anomaly signals, prediction — 12 AI prediction signals) and their sub-categories. 2. Search News POST /open/news_search is the primary search endpoint. Get latest news: curl -s -X POST "https://ai.6551.io/open/news_search" \ -H "Authorization: Bearer $OPENNEWS_TOKEN " \ -H "Content-Type: application/json" \ -d '{"limit": 10, "page": 1}' Search by keyword: curl -s -X POST "https://ai.6551.io/open/news_search" \ -H "Authorization: Bearer $OPENNEWS_TOKEN " \ -H "Content-Type: application/json" \ -d '{"q": "bitcoin OR ETF", "limit": 10, "page": 1}' Search by coin symbol: curl -s -X POST "https://ai.6551.io/open/news_search" \ -H "Authorization: Bearer $OPENNEWS_TOKEN " \ -H "Content-Type: application/json" \ -d '{"coins": ["BTC"], "limit": 10, "page": 1}' Filter by engine type and news type: curl -s -X POST "https://ai.6551.io/open/news_search" \ -H "Authorization: Bearer $OPENNEWS_TOKEN " \ -H "Content-Type: application/json" \ -d '{"engineTypes": {"news": ["Bloomberg", "Reuters"]}, "limit": 10, "page": 1}' Only news with coins: curl -s -X POST "https://ai.6551.io/open/news_search" \ -H "Authorization: Bearer $OPENNEWS_TOKEN " \ -H "Content-Type: application/json" \ -d '{"hasCoin": true, "limit": 10, "page": 1}' News Search Parameters Parameter Type Required Description limit integer yes Max results per page (1-100) page integer yes Page number (1-based) q string no Full-text keyword search coins string[] no Filter by coin symbols (e.g. ["BTC","ETH"] ) engineTypes map[string][]string no Filter by engine and news types hasCoin boolean no Only return news with associated coins score integer no Filter by minimum AI score (0-100) 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. Strategy History Operations These authenticated endpoints query the current user's strategy configuration and historical strategy-triggered events. Each call consumes 1 quota. Create and manage strategies at https://www.newsliquid.com/strategy . 1. Get Strategy List curl -s -H "Authorization: Bearer $OPENNEWS_TOKEN " \ "https://ai.6551.io/open/strategy_list?page=1&limit=20" Returns only id , name , description , enabled , and createdAt for each strategy. 2. Get Strategy Hits curl -s -H "Authorization: Bearer $OPENNEWS_TOKEN " \ "https://ai.6551.io/open/strategy_hits?strategyId=42&page=1&limit=20" Returns historical triggered events for the given strategy ID. Each hit uses the same news-like payload shape as the WebSocket strategy.triggered event, including nested strategy , coins , optional aiRating , source , description , relatedAddress , and triggered metric fields when available. WebSocket news_wss Protocol Connect with the token in the query string: wss://ai.6551.io/open/news_wss?token=$OPENNEWS_TOKEN Supported client messages: Client sends Server returns text frame ping text frame pong JSON-RPC news.subscribe with optional engineTypes , coins , hasCoin JSON-RPC response with matching id and result.success=true JSON-RPC news.unsubscribe JSON-RPC response with matching id and result.success=true Server-pushed events: Server method Meaning news.update New matched news item news.ai_update New matched news item with AI rating fields strategy.triggered Strategy hit for the authenticated user who owns the strategy news.subscribe controls news.update and news.ai_update . strategy.triggered is automatically delivered to the authenticated strategy owner and does not need a separate subscribe method. Subscribe example: { "jsonrpc" : "2.0" , "id" : 1 , "method" : "news.subscribe" , "params" : { "engineTypes" : { "news" : [ "Bloomberg" , "CoinDesk" ] , "onchain" : [ ] } , "coins" : [ "BTC" , "ETH" ] , "hasCoin" : true } } Unsubscribe example: { "jsonrpc" : "2.0" , "id" : 2 , "method" : "news.unsubscribe" } Finance Enhancement Entity Protocol These authenticated endpoints provide company discovery, report catalogs, report text, key market events, public stock-disclosure evidence, and wallet-visible on-chain evidence. Responses are wrapped as {"success": true, "data": ...} and may include usage quota metadata. Treat data.status as the business result; HTTP success alone does not mean the company, report, or disclosure query was resolved. Resolve the Company Before Reading Reports Company names can legitimately map to more than one issuer or listed security. Use this sequence: user company expression → broad company-search → inspect ambiguity_candidates[] → choose the intended market/issuer → retry with one exact identifier namespace → read company-info → choose report_id + report_type → read company-report-text Never send a fuzzy company name together with an exact identifier. Exactly one company selector must be authoritative. The OpenNews MCP tools accept any one of these selectors directly: MCP selector Example Meaning canonical_issuer_id SEC:0002120882 Stable issuer ID returned by company search ticker SKHY Exact listed ticker cik 0002120882 SEC CIK krx_stock_code 000660 Six-digit KRX security code dart_corp_code 00164779 Eight-digit DART issuer code identifier + identifier_type + market 00164779 + dart_corp_code + KR Generic typed selector company / search keyword SK hynix Inc. / Hynix Fuzzy discovery only The raw HTTP endpoints use the generic form identifier + identifier_type + market . Do not send cik , ticker , dart_corp_code , krx_stock_code , or canonical_issuer_id as standalone HTTP JSON fields: those are MCP conveniences. Convert stable IDs as follows: Search result Exact raw HTTP selector SEC:0002120882 {"identifier":"0002120882","identifier_type":"cik","market":"US"} DART:00164779 {"identifier":"00164779","identifier_type":"dart_corp_code","market":"KR"} KRX:000660 security {"identifier":"000660","identifier_type":"krx_stock_code","market":"KR"} Company Search Use a name only for discovery. An ambiguous_entity response is expected when multiple markets or issuers match. curl -s -X POST "https://ai.6551.io/open/finance-enhance/company-search" \ -H "Authorization: Bearer $OPENNEWS_TOKEN " \ -H "Content-Type: application/json" \ -d '{"keyword":"Hynix","identifier_type":"company_name","market":"GLOBAL","result_scope":"issuer","limit":20,"auto_collect":false}' For SK hynix this can return both the U.S. SEC issuer ( SEC:0002120882 , including ticker SKHY ) and the Korean DART issuer ( DART:00164779 , security KRX:000660 ). Choose from the user's requested market; do not silently take the first candidate. Company Info Returns the resolved identity and available SEC/DART filings, third-party research reports, earnings-call transcripts, report forms, and financial item names. U.S. SEC issuer: curl -s -X POST "https://ai.6551.io/open/finance-enhance/company-info" \ -H "Authorization: Bearer $OPENNEWS_TOKEN " \ -H "Content-Type: application/json" \ -d '{"identifier":"0002120882","identifier_type":"cik","market":"US","auto_collect":false,"filing_limit":50,"fact_limit":1000}' Korean DART issuer: curl -s -X POST "https://ai.6551.io/open/finance-enhance/company-info" \ -H "Authorization: Bearer $OPENNEWS_TOKEN " \ -H "Content-Type: application/json" \ -d '{"identifier":"00164779","identifier_type":"dart_corp_code","market":"KR","auto_collect":false,"filing_limit":50,"fact_limit":1000}' Verify the returned canonical_issuer_id , market , matched_by , and match_confidence before using any report catalog entry. Company Report Text
Keywords that activate this skill. Click one to copy it.

This skill does not provide trigger words.

The downloaded .skill package contains the following fields.
Field Description
formatFormat tag (skill/v1)
skill_idUnique skill ID
nameSkill name
versionVersion
descriptionDescription
categoryCategories (array)
trigger_wordsTrigger words
tagsTags
sourceSource
source_urlSource URL (this page)
exported_atExported at (set per download)
system_promptSystem prompt body
model_configModel config: provider / model / temperature / max_tokens / top_p
examplesExamples
install_guideImport guide for Coze / Dify / Claude / custom frameworks
The same skill can be exported in different platform formats.
.skill Standard format with system_prompt and model_config, ready for any agent framework Download
.skillpro Enhanced format with scripts, tools, dependencies and hooks Download
.json Plain JSON export with system_prompt and model parameters only Download
Coze Markdown with frontmatter, for Coze platform import Download
Dify Dify DSL, import directly after creating an app Download

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

验证码 --

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。