PluginBench
Skill
Review
Audit score 70

opennews

6551team/opennews-mcp

Real-time financial market news from 84+ sources with AI-analyzed trading signals and impact scores.

What is opennews?

OpenNews aggregates crypto, equities, macro, and financial market news across 84+ sources including Bloomberg, Reuters, CoinDesk, and on-chain whale trades. Use it to monitor market-moving signals, trading opportunities, and AI-predicted price movements across digital assets, stocks, commodities, and policy.

  • Search and filter news from 53+ news outlets, 9 exchanges, 3 on-chain trackers, and 12 AI prediction signals
  • Get AI-analyzed impact scores (0-100), trading signals (long/short/neutral), and bilingual summaries for each article
  • Filter by coin symbols, engine type (news/listing/onchain/meme/market/prediction), minimum impact score, and keyword
  • Access whale trades, large liquidations, funding rate changes, and meme coin sentiment
  • Use free endpoints without authentication for curated hot news by category
  • Monitor price spikes, smart money trades, insider patterns, and correlation-based predictions

How to install opennews

npx skills add https://github.com/6551team/opennews-mcp --skill opennews
Prerequisites
  • curl installed (can be installed via brew on macOS/Linux)
  • OPENNEWS_TOKEN from https://6551.io/mcp (optional; free endpoints available without token)
Claude Code
Cursor
Windsurf
Cline

How to use opennews

  1. 1.Set OPENNEWS_TOKEN environment variable with your token from https://6551.io/mcp (or skip for free tier)
  2. 2.Call GET /open/free_categories to see available news categories if using free tier, or POST /open/news_type for full source tree with token
  3. 3.Use POST /open/news_search with parameters like limit, page, q (keyword), coins (symbols), engineTypes, score, or hasCoin to search news
  4. 4.Parse the response to extract text, newsType, aiRating.score, aiRating.signal, and aiRating.summary for each article
  5. 5.Filter results by impact score (score ≥80 for high-impact) and trading signal (long/short) to prioritize actionable news

Use cases

Good for
  • Monitor breaking news across crypto and equities to identify trading opportunities before price moves
  • Track whale positions and large liquidations on Hyperliquid and other exchanges for market sentiment
  • Search for news about specific coins (e.g., BTC, ETH) with AI impact scores to prioritize high-signal events
  • Filter high-impact news (score ≥80) across Bloomberg, Reuters, and CoinDesk for institutional-grade signals
  • Monitor AI prediction signals like SMART_MONEY_TRADE and PRICE_SPIKE for early entry/exit signals
Who it's for
  • Crypto traders and investors monitoring digital asset markets
  • Equity traders tracking semiconductor, AI infrastructure, and supply chain news
  • Macro analysts following commodities, rates, and policy developments
  • Quantitative traders using AI signals and on-chain data for systematic strategies
  • Financial analysts needing real-time multi-source news aggregation

opennews FAQ

Do I need a token to use OpenNews?

No. Free endpoints (/open/free_categories and /open/free_hot) provide curated hot news and trending tweets without authentication. Full search and 84+ sources require OPENNEWS_TOKEN from https://6551.io/mcp.

What are the 6 engine categories?

News (53 sources: Bloomberg, Reuters, FT, CNBC, CoinDesk, etc.), Listing (9 exchanges: Binance, Coinbase, OKX, etc.), OnChain (3 whale/KOL trackers), Meme (1 Twitter sentiment source), Market (6 anomaly signals: price, funding, liquidations), and Prediction (12 AI signals: smart money, price spike, insider pattern, etc.).

How do I search for news about a specific coin?

Use POST /open/news_search with the coins parameter, e.g., {"coins": ["BTC", "ETH"], "limit": 10, "page": 1}. Optionally add score ≥80 to filter high-impact news.

What do the AI rating fields mean?

score (0-100) is impact severity, grade (A-F) is letter grade, signal (long/short/neutral) is trading direction, and summary/enSummary are bilingual AI-generated summaries of the article's market relevance.

Can I search by keyword and filter by source?

Yes. Use q for full-text search (supports OR/AND operators) and engineTypes to filter by specific sources, e.g., {"q": "bitcoin OR ETF", "engineTypes": {"news": ["Bloomberg", "Reuters"]}, "limit": 10, "page": 1}.

Full instructions (SKILL.md)

Source of truth, from 6551team/opennews-mcp.


name: opennews description: "Real-time crypto, equities, macro, and financial market news aggregator — 84+ 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, whale/KOL 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: - curl optionalEnv: - OPENNEWS_TOKEN primaryEnv: OPENNEWS_TOKEN emoji: "\U0001F4F0" install: - id: curl kind: brew formula: curl label: curl (HTTP client) os: - darwin - linux - win32 version: 1.0.5

OpenNews Financial Market News Skill

Real-time crypto, equities, macro, and financial market news aggregator powered by 6551.io — 84+ 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 — 84+ Sources Across 6 Categories

CategoryCountKey Sources
News53Bloomberg, 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, and more; useful for crypto, U.S. equities, semiconductors, AI infrastructure, supply chains, commodities, rates, policy, and market-moving social/news signals
Listing9Binance, Coinbase, OKX, Bybit, Upbit, Bithumb, Robinhood, Hyperliquid, Aster
OnChain3Hyperliquid Whale Trade, Hyperliquid Large Position, KOL Trade
Meme1Twitter meme coin social sentiment
Market6Price Change, Funding Rate, Funding Rate Difference, Large Liquidation, Market Trends, OI Change
Prediction12CORRELATION_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 84+ sources.

curl -s -H "Authorization: Bearer $OPENNEWS_TOKEN" \
  "https://ai.6551.io/open/news_type"

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, 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

ParameterTypeRequiredDescription
limitintegeryesMax results per page (1-100)
pageintegeryesPage number (1-based)
qstringnoFull-text keyword search
coinsstring[]noFilter by coin symbols (e.g. ["BTC","ETH"])
engineTypesmap[string][]stringnoFilter by engine and news types
hasCoinbooleannoOnly return news with associated coins
scoreintegernoFilter 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.


Data Structures

News Article

{
  "id": "unique-article-id",
  "text": "Article headline / content",
  "newsType": "Bloomberg",
  "engineType": "news",
  "link": "https://...",
  "coins": [{"symbol": "BTC", "market_type": "cex", "match": "title"}],
  "aiRating": {
    "score": 85,
    "grade": "A",
    "signal": "long",
    "status": "done",
    "summary": "Chinese summary",
    "enSummary": "English summary"
  },
  "ts": 1708473600000
}

Common Workflows

Quick Market Overview

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}' | jq '.data[] | {text, newsType, signal: .aiRating.signal}'

High-Impact News (score >= 80)

curl -s -X POST "https://ai.6551.io/open/news_search" \
  -H "Authorization: Bearer $OPENNEWS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"score": 80, "limit": 50, "page": 1}'

Free API Endpoints (No Token Required)

If you don't have an OPENNEWS_TOKEN, you can use these free endpoints as a fallback. These provide curated hot news and trending tweets by category, but with limited search capabilities compared to the authenticated API.

1. Get Free News Categories

Get all available news categories and subcategories for the free tier.

curl -s -X GET "https://ai.6551.io/open/free_categories"

2. Get Hot News by Category

Get hot news articles and trending tweets by category. No authentication required.

curl -s -X GET "https://ai.6551.io/open/free_hot?category=macro"

Parameters:

ParameterTypeRequiredDescription
categorystringyesCategory key from free_categories
subcategorystringnoSubcategory key for more specific filtering

Response Structure:

{
  "success": true,
  "category": "crypto",
  "subcategory": "defi",
  "news": {
    "success": true,
    "count": 10,
    "items": [
      {
        "id": 123,
        "title": "...",
        "source": "...",
        "link": "https://...",
        "score": 85,
        "grade": "A",
        "signal": "bullish",
        "summary_zh": "...",
        "summary_en": "...",
        "coins": ["BTC", "ETH"],
        "published_at": "2026-03-17T10:00:00Z"
      }
    ]
  },
  "tweets": {
    "success": true,
    "count": 5,
    "items": [
      {
        "author": "Vitalik Buterin",
        "handle": "VitalikButerin",
        "content": "...",
        "url": "https://...",
        "metrics": { "likes": 1000, "retweets": 200, "replies": 50 },
        "posted_at": "2026-03-17T09:00:00Z",
        "relevance": "high"
      }
    ]
  }
}

Example - Get Hot Macro News:

curl -s -X GET "https://ai.6551.io/open/free_hot?category=macro"

Example - Get DeFi Subcategory News:

curl -s -X GET "https://ai.6551.io/open/free_hot?category=macro&subcategory=defi"

Notes

  • Primary API: Get your token at https://6551.io/mcp for full access to 84+ sources with advanced search
  • Free API: Use free endpoints as fallback when token is unavailable (limited to curated hot news)
  • Rate limits apply; max 100 results per request for authenticated API
  • AI ratings may not be available on all articles (check status == "done")
  • Free API data is cached and updated periodically; if data is still being generated, a 503 response will be returned