xfinlab
Real-time market events, sentiment, and technical analysis as MCP tools, backed by real data.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"xfinlab": {
"url": "https://api.xfinlab.com/api/mcp"
}
}
}遠端端點
https://api.xfinlab.com/api/mcpstreamable-http它能做什麼
工具清單
工具（5）
🟢get_market_events(api_key, marketplace_license_key, ticker, limit)
Get recent market/company news headlines from XFINLAB's aggregated real-time news feed (RSS-sourced, deduplicated). Optionally filter by ticker/company name. Returns title, source, kind, published_at, url for each item -- no article body text.
輸入結構描述
{
"type": "object",
"properties": {
"api_key": {
"type": "string",
"description": "XFINLAB Intelligence API key (X-API-Key). Omit if supplied via HTTP header instead."
},
"marketplace_license_key": {
"type": "string",
"description": "Optional: an mcp-marketplace.io license key for this listing's paid tier. If valid, upgrades a free XFINLAB API key's daily quota to Pro for this call. Omit if supplied via the X-Marketplace-License-Key header instead, or if not using a marketplace license."
},
"ticker": {
"type": "string",
"description": "Optional ticker or company name to filter by, e.g. 'NVDA'."
},
"limit": {
"type": "integer",
"description": "Max results, 1-100.",
"default": 20
}
},
"required": []
}🟢get_sentiment(api_key, marketplace_license_key, ticker, limit)
Get FinBERT-based sentiment analysis of recent headlines for a ticker. Returns per-headline label/confidence/score plus an average score. Real model inference, not a fabricated estimate.
輸入結構描述
{
"type": "object",
"properties": {
"api_key": {
"type": "string",
"description": "XFINLAB Intelligence API key (X-API-Key). Omit if supplied via HTTP header instead."
},
"marketplace_license_key": {
"type": "string",
"description": "Optional: an mcp-marketplace.io license key for this listing's paid tier. If valid, upgrades a free XFINLAB API key's daily quota to Pro for this call. Omit if supplied via the X-Marketplace-License-Key header instead, or if not using a marketplace license."
},
"ticker": {
"type": "string",
"description": "Ticker to analyze, e.g. 'AAPL'."
},
"limit": {
"type": "integer",
"description": "Number of recent headlines to analyze, 1-25.",
"default": 10
}
},
"required": [
"ticker"
]
}🟢get_technical_analysis(api_key, marketplace_license_key, ticker, period, interval, ...)
Get confluence direction/confidence, trend, MACD, volume, chart patterns, and market-structure signals (BOS/CHOCH/liquidity-sweep/order-flow/volume-profile/institutional-footprint) for one ticker, computed from real OHLC price data -- the same engine that powers XFINLAB's chart-analysis and ai-analysis pages.
輸入結構描述
{
"type": "object",
"properties": {
"api_key": {
"type": "string",
"description": "XFINLAB Intelligence API key (X-API-Key). Omit if supplied via HTTP header instead."
},
"marketplace_license_key": {
"type": "string",
"description": "Optional: an mcp-marketplace.io license key for this listing's paid tier. If valid, upgrades a free XFINLAB API key's daily quota to Pro for this call. Omit if supplied via the X-Marketplace-License-Key header instead, or if not using a marketplace license."
},
"ticker": {
"type": "string",
"description": "Ticker to analyze, e.g. 'TSLA', '0700.HK'."
},
"period": {
"type": "string",
"description": "History window, e.g. '6mo', '1y'.",
"default": "6mo"
},
"interval": {
"type": "string",
"description": "Candle interval, e.g. '1d'.",
"default": "1d"
},
"lang": {
"type": "string",
"description": "Language for text labels, e.g. 'en', 'zh-HK'.",
"default": "en"
}
},
"required": [
"ticker"
]
}🟢get_intelligence_feed(api_key, marketplace_license_key, ticker, limit, lang)
Get AI-structured event clusters from recent news: same-story headline clusters with entity/sentiment/quant-context fields and an AI-written narrative summary. Optionally scoped to one ticker; otherwise returns the latest cross-market feed. This is structured fact extraction, not republished article text, and never includes a directional trading signal or probability estimate.
輸入結構描述
{
"type": "object",
"properties": {
"api_key": {
"type": "string",
"description": "XFINLAB Intelligence API key (X-API-Key). Omit if supplied via HTTP header instead."
},
"marketplace_license_key": {
"type": "string",
"description": "Optional: an mcp-marketplace.io license key for this listing's paid tier. If valid, upgrades a free XFINLAB API key's daily quota to Pro for this call. Omit if supplied via the X-Marketplace-License-Key header instead, or if not using a marketplace license."
},
"ticker": {
"type": "string",
"description": "Optional ticker to scope the feed to, e.g. 'MSFT'."
},
"limit": {
"type": "integer",
"description": "Max event clusters, 1-10.",
"default": 5
},
"lang": {
"type": "string",
"description": "Language for the narrative summary.",
"default": "en"
}
},
"required": []
}🟢get_global_market_map(api_key, marketplace_license_key, regions, news_limit, include_sentiment)
Get a cross-region global market snapshot ('World Engine'): macro indicators (GDP growth/inflation/unemployment, with source attribution -- world_bank/fred/ecb), filtered regional headlines, and FinBERT sentiment for each requested region, plus a top-level global headlines feed (GDELT). Regions: us, europe, japan, korea, china, hk, tw, sea, me, latam. No AI narrative, no directional signal -- structured real data only.
輸入結構描述
{
"type": "object",
"properties": {
"api_key": {
"type": "string",
"description": "XFINLAB Intelligence API key (X-API-Key). Omit if supplied via HTTP header instead."
},
"marketplace_license_key": {
"type": "string",
"description": "Optional: an mcp-marketplace.io license key for this listing's paid tier. If valid, upgrades a free XFINLAB API key's daily quota to Pro for this call. Omit if supplied via the X-Marketplace-License-Key header instead, or if not using a marketplace license."
},
"regions": {
"type": "string",
"description": "Comma-separated region keys, e.g. 'us,hk,china'. Omit for all 10 regions."
},
"news_limit": {
"type": "integer",
"description": "Headlines per region, 1-20.",
"default": 6
},
"include_sentiment": {
"type": "boolean",
"description": "Whether to run FinBERT sentiment on each region's headlines.",
"default": true
}
},
"required": []
}社群
證據