Skip to main content
Glama
deenesjakoruzh
botextractai

Finance MCP Server

by botextractai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

MCP (Model Context Protocol)-Server und -Client mit FastMCP und LangChain

Dieses Beispiel erstellt einen lokalen MCP -Server mit FastMCP und erstellt einen LangChain Artificial Intelligence-Agenten, der die im MCP-Server definierten Tools verwendet.

Das Erstellen von MCP-Servern erfordert in der Regel viel Standardcode und Konfiguration. FastMCP vereinfacht die Einrichtung von MCP-Servern erheblich.

LangChain MCP-Adapter können problemlos eine Verbindung zu lokalen oder externen MCP-Servern herstellen.

Dieses Beispiel verwendet FastMCP, um einen lokalen MCP-Server zu erstellen und anschließend LangChain MCP-Adapter auf der Clientseite. Da dieses Beispiel ein OpenAI Large Language Model (LLM) verwendet, nutzt es auch die OpenAI-Implementierung von LangChain zur Kommunikation mit dem LLM. Es erstellt einen LangGraph ReAct (Reasoning and Acting)-Agenten. Asyncio wird für asynchrone Funktionen benötigt.

Da in diesem Beispiel ein lokaler MCP-Server verwendet wird, nutzt die Verbindung („Transport“) stdio (Python-Standard-Ein-/Ausgabeströme). Ein externer MCP-Server würde anstelle von stdio Server-Sent Events (SSE) oder WebSockets-Transport erfordern.

Dem LLM können alle möglichen Fragen zu einer Aktie gestellt werden. Anschließend ruft der LLM die im MCP-Server definierten Tools auf, sammelt alle Informationen und antwortet mit den gesammelten Informationen.

In diesem Beispiel wird gefragt:

What company uses the stock ticker META and how did this company's revenue develop over the last quarters and years?

YFinance bietet Börsentools für den MCP-Server. YFinance ist eine Python-Bibliothek für den Zugriff auf Finanzdaten von Yahoo Finance. YFinance benötigt keinen API-Schlüssel.

Erforderlicher API-Schlüssel für dieses Beispiel

Für dieses Beispiel benötigen Sie einen OpenAI-API-Schlüssel. Ihren erhalten Sie hier. Fügen Sie den OpenAI-API-Schlüssel in die Datei .env.example ein und benennen Sie diese anschließend in .env um (entfernen Sie die Endung „.example“).

Related MCP server: MCP Yahoo Finance

Führen Sie dieses Beispiel aus

Führen Sie die Anwendung über die Befehlszeile aus mit:

python mcp_client.py

Beispielergebnisse

Wie Sie der Antwort entnehmen können, wurden alle 3 im MCP-Server definierten Tools verwendet:

Match 1:
{"address1": "1 Meta Way", "city": "Menlo Park", "state": "CA", "zip": "94025", "country": "United States", "phone": "650 543 4800", "website": "https://investor.atmeta.com", "industry": "Internet Content & Information", "industryKey": "internet-content-information", "industryDisp": "Internet Content & Information", "sector": "Communication Services", "sectorKey": "communication-services", "sectorDisp": "Communication Services", "longBusinessSummary": "Meta Platforms, Inc. engages in the development of products that enable people to connect and share with friends and family through mobile devices, personal computers, virtual reality and mixed reality headsets, augmented reality, and wearables worldwide. It operates through two segments, Family of Apps (FoA) and Reality Labs (RL). The FoA segment offers Facebook, which enables people to build community through feed, reels, stories, groups, marketplace, and other; Instagram that brings people closer through instagram feed, stories, reels, live, and messaging; Messenger, a messaging application for people to connect with friends, family, communities, and businesses across platforms and devices through text, audio, and video calls; Threads, an application for text-based updates and public conversations; and WhatsApp, a messaging application that is used by people and businesses to communicate and transact in a private way. The RL segment provides virtual, augmented, and mixed reality related products comprising consumer hardware, software, and content that help people feel connected, anytime, and anywhere. The company was formerly known as Facebook, Inc. and changed its name to Meta Platforms, Inc. in October 2021. The company was incorporated in 2004 and is headquartered in Menlo Park, California.", "fullTimeEmployees": 76834, "companyOfficers": [{"maxAge": 1, "name": "Mr. Mark Elliot Zuckerberg", "age": 40, "title": "Founder, Chairman & CEO", "yearBorn": 1984, "fiscalYear": 2024, "totalPay": 27219874, "exercisedValue": 0, "unexercisedValue": 0}, {"maxAge": 1, "name": "Ms. Susan J. S. Li", "age": 38, "title": "Chief Financial Officer", "yearBorn": 1986, "fiscalYear": 2024, "totalPay": 1948846, "exercisedValue": 0, "unexercisedValue": 0}, {"maxAge": 1, "name": "Mr. Javier  Olivan", "age": 47, "title": "Chief Operating Officer", "yearBorn": 1977, "fiscalYear": 2024, "totalPay": 3835042, "exercisedValue": 0, "unexercisedValue": 0}, {"maxAge": 1, "name": "Mr. Andrew  Bosworth", "age": 42, "title": "Chief Technology Officer", "yearBorn": 1982, "fiscalYear": 2024, "totalPay": 1923184, "exercisedValue": 0, "unexercisedValue": 0}, {"maxAge": 1, "name": "Mr. Christopher K. Cox", "age": 41, "title": "Chief Product Officer", "yearBorn": 1983, "fiscalYear": 2024, "totalPay": 1937677, "exercisedValue": 0, "unexercisedValue": 0}, {"maxAge": 1, "name": "Mr. Dana  White", "title": "Independent Director", "fiscalYear": 2024, "totalPay": 272, "exercisedValue": 0, "unexercisedValue": 0}, {"maxAge": 1, "name": "Mr. Aaron A. Anderson", "title": "Chief Accounting Officer", "fiscalYear": 2024, "exercisedValue": 0, "unexercisedValue": 0}, {"maxAge": 1, "name": "Mr. Atish  Banerjea", "age": 58, "title": "Chief Information Officer", "yearBorn": 1966, "fiscalYear": 2024, "exercisedValue": 0, "unexercisedValue": 0}, {"maxAge": 1, "name": "Ms. Jennifer G. Newstead J.D.", "age": 53, "title": "Chief Legal Officer", "yearBorn": 1971, "fiscalYear": 2024, "totalPay": 3079624, "exercisedValue": 0, "unexercisedValue": 0}, {"maxAge": 1, "name": "Mr. Henry T. A. Moniz", "age": 59, "title": "Chief Compliance Officer", "yearBorn": 1965, "fiscalYear": 2024, "exercisedValue": 0, "unexercisedValue": 0}], "auditRisk": 10, "boardRisk": 10, "compensationRisk": 10, "shareHolderRightsRisk": 10, "overallRisk": 10, "governanceEpochDate": 1746057600, "compensationAsOfEpochDate": 1735603200, "executiveTeam": [], "maxAge": 86400, "priceHint": 2, "previousClose": 599.27, "open": 592.525, "dayLow": 586.58, "dayHigh": 596.0, "regularMarketPreviousClose": 599.27, "regularMarketOpen": 592.525, "regularMarketDayLow": 586.58, "regularMarketDayHigh": 596.0, "dividendRate": 2.1, "dividendYield": 0.36, "exDividendDate": 1741910400, "payoutRatio": 0.0792, "beta": 1.237, "trailingPE": 22.932838, "forwardPE": 23.213835, "volume": 10332250, "regularMarketVolume": 10332250, "averageVolume": 18515718, "averageVolume10days": 18570790, "averageDailyVolume10Day": 18570790, "bid": 586.18, "ask": 588.22, "bidSize": 1, "askSize": 1, "marketCap": 1506761506816, "fiftyTwoWeekLow": 442.65, "fiftyTwoWeekHigh": 740.91, "priceToSalesTrailing12Months": 8.844573, "fiftyDayAverage": 580.1932, "twoHundredDayAverage": 580.8713, "trailingAnnualDividendRate": 2.025, "trailingAnnualDividendYield": 0.0033791114, "currency": "USD", "tradeable": false, "enterpriseValue": 1455978577920, "profitMargins": 0.39113998, "floatShares": 2166796937, "sharesOutstanding": 2181270016, "sharesShort": 31512402, "sharesShortPriorMonth": 24545066, "sharesShortPreviousMonthDate": 1741910400, "dateShortInterest": 1744675200, "sharesPercentSharesOut": 0.0125, "heldPercentInsiders": 0.00089, "heldPercentInstitutions": 0.80194, "shortRatio": 1.45, "shortPercentOfFloat": 0.0145000005, "impliedSharesOutstanding": 2565530112, "bookValue": 73.337, "priceToBook": 8.008372, "lastFiscalYearEnd": 1735603200, "nextFiscalYearEnd": 1767139200, "mostRecentQuarter": 1743379200, "earningsQuarterlyGrowth": 0.346, "netIncomeToCommon": 66635001856, "trailingEps": 25.61, "forwardEps": 25.3, "enterpriseToRevenue": 8.546, "enterpriseToEbitda": 16.549, "52WeekChange": 0.24272108, "SandP52WeekChange": 0.08081472, "lastDividendValue": 0.525, "lastDividendDate": 1741910400, "quoteType": "EQUITY", "currentPrice": 587.31, "targetHighPrice": 935.0, "targetLowPrice": 466.0, "targetMeanPrice": 703.8915, "targetMedianPrice": 690.0, "recommendationMean": 1.45588, "recommendationKey": "strong_buy", "numberOfAnalystOpinions": 62, "totalCash": 70229999616, "totalCashPerShare": 27.932, "ebitda": 87979999232, "totalDebt": 49519001600, "quickRatio": 2.501, "currentRatio": 2.662, "totalRevenue": 170359996416, "debtToEquity": 26.763, "revenuePerShare": 67.349, "returnOnAssets": 0.17879999, "returnOnEquity": 0.39835, "grossProfits": 139297996800, "freeCashflow": 36658999296, "operatingCashflow": 96108003328, "earningsGrowth": 0.365, "revenueGrowth": 0.161, "grossMargins": 0.81767, "ebitdaMargins": 0.51644003, "operatingMargins": 0.41487, "financialCurrency": "USD", "symbol": "META", "language": "en-US", "region": "US", "typeDisp": "Equity", "quoteSourceName": "Nasdaq Real Time Price", "triggerable": true, "customPriceAlertConfidence": "HIGH", "longName": "Meta Platforms, Inc.", "exchange": "NMS", "messageBoardId": "finmb_20765463", "exchangeTimezoneName": "America/New_York", "exchangeTimezoneShortName": "EDT", "gmtOffSetMilliseconds": -14400000, "market": "us_market", "esgPopulated": false, "regularMarketChangePercent": -1.9957651, "regularMarketPrice": 587.31, "shortName": "Meta Platforms, Inc.", "hasPrePostMarketData": true, "firstTradeDateMilliseconds": 1337347800000, "postMarketChangePercent": 0.929666, "postMarketPrice": 592.77, "postMarketChange": 5.46002, "regularMarketChange": -11.960022, "regularMarketDayRange": "586.58 - 596.0", "fullExchangeName": "NasdaqGS", "averageDailyVolume3Month": 18515718, "fiftyTwoWeekLowChange": 144.66, "fiftyTwoWeekLowChangePercent": 0.3268045, "fiftyTwoWeekRange": "442.65 - 740.91", "fiftyTwoWeekHighChange": -153.59998, "fiftyTwoWeekHighChangePercent": -0.2073126, "fiftyTwoWeekChangePercent": 24.272108, "dividendDate": 1742947200, "earningsTimestamp": 1746043503, "earningsTimestampStart": 1753786740, "earningsTimestampEnd": 1754308800, "earningsCallTimestampStart": 1746046800, "earningsCallTimestampEnd": 1746046800, "isEarningsDateEstimate": true, "epsTrailingTwelveMonths": 25.61, "epsForward": 25.3, "epsCurrentYear": 25.53311, "priceEpsCurrentYear": 23.001898, "fiftyDayAverageChange": 7.1168213, "fiftyDayAverageChangePercent": 0.012266296, "twoHundredDayAverageChange": 6.4387207, "twoHundredDayAverageChangePercent": 0.011084591, "sourceInterval": 15, "exchangeDataDelayedBy": 0, "ipoExpectedDate": "2022-06-09", "averageAnalystRating": "1.5 - Strong Buy", "cryptoTradeable": false, "marketState": "PREPRE", "corporateActions": [], "postMarketTime": 1746575989, "regularMarketTime": 1746561600, "displayName": "Meta Platforms", "trailingPegRatio": 1.9916}

Match 2:
           Tax Effect Of Unusual Items  ... Operating Revenue
2025-03-31             21935371.559134  ...     41804000000.0
2024-12-31               -44365234.375  ...     47866000000.0
2024-09-30                   1320000.0  ...     40155000000.0
2024-06-30                 -18480000.0  ...     38682000000.0
2024-03-31            -18929140.520341  ...     36075000000.0

[5 rows x 45 columns]

Match 3:
           Tax Effect Of Unusual Items  ... Operating Revenue
2024-12-31                 -81420000.0  ...    162779000000.0
2023-12-31                 -64416000.0  ...    133844000000.0
2022-12-31                 -15795000.0  ...    115801000000.0
2021-12-31                 -23380000.0  ...    117208000000.0
2020-12-31                         NaN  ...               NaN

[5 rows x 48 columns]

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityActive
ResponsivenessNo issues

Resources

Related MCP Connectors

  • GloomB
    sh.gloom.api

    Financial data MCP server for Claude, ChatGPT, Cursor and Codex. Real-time stock quotes, financial statements, options flow, SEC filings, insider trades, 13F holdings, macro data and market news from gloom.sh, the open-source Bloomberg Terminal alternative.

    FinanceResearch & Data
    701
  • AIsa FinanceAOAuth
    one.aisa

    Your agent needs markets — prices and fundamentals for listed companies, the filings behind them, crypto, and what the prediction markets put the odds at. **What you can ask for** • "Pull this company's income statement, cash flow and balance sheet for the last 8 quarters." • "What did insiders buy or sell, and when?" • "Snapshot prices for these 50 tickers, then the OHLC history for the three that moved." • "What are the current odds on this event across Kalshi and Polymarket?" • "Screen for companies matching these financial criteria." **How to use it** Point any MCP client at https://mcp.aisa.one/finance/mcp and sign in with OAuth — there is no key to create or paste. 49 tools: prices and snapshots, income statements, balance sheets and cash flows, metrics and ratios, earnings and analyst estimates, filings and line-item search, insider trades, macro interest rates, news, a screener; CoinGecko spot prices, market tables, OHLC, per-venue tickers and trending; Kalshi and Polymarket markets and trades; plus EDINET filings for Japan. **Why this rather than the source** Equities, crypto and event markets behind one account, so a cross-asset question is one conversation. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Read the number here, then ask the same agent what X is saying about the ticker today — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/marketpulse/mcp · /crypto-market-data/mcp · /prediction-market-data/mcp · /stock-pulse/mcp for one slice each.

    CryptocurrencyFinance
    541
  • china-market-intelligence-mcpOAuth
    com.thenextgennexus

    MCP server giving AI agents one-connection access to China A-share market intelligence: financials,

    FinanceResearch & Data
    2
  • AIsa EquitiesAOAuth
    one.aisa

    Your agent needs company financials it can compute on — statements, ratios, earnings, estimates, filings and insider activity as structured data, not a PDF. **What you can ask for** • "Give me 8 quarters of income statement, balance sheet and cash flow for this ticker." • "What do analysts estimate for next quarter, and how did the last four surprise?" • "Find this exact line item across every filing." • "Who bought or sold as an insider in the last 90 days?" • "Screen for profitable companies under this valuation with growing revenue." **How to use it** Point any MCP client at https://mcp.aisa.one/marketpulse/mcp and sign in with OAuth — there is no key to create or paste. 21 tools: prices and snapshots, income statements, balance sheets, cash-flow statements, financial metrics and snapshots, earnings, analyst estimates, company facts, filings and filing items, line-item search, a screener, insider trades, macro interest rates, news, plus EDINET documents and filing digests for Japanese issuers. **Why this rather than the source** Statements as fields you can compute on, and a screener in the same place. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Read the fundamentals here, then ask the same agent what social is saying about the ticker — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/finance/mcp for equities, crypto and prediction markets in one place.

    FinanceResearch & Data
    261

Related MCP Servers

  • StockFlow MCP Server

    twolven
    A
    license
    B
    quality
    B
    maintenance
    A Model Context Protocol server providing real-time stock data and options analysis through Yahoo Finance, enabling LLMs to access market data, analyze stocks, and evaluate options strategies.
    3
    27
    MIT

  • MCP Yahoo Finance

    maxscheijen
    A
    license
    B
    quality
    A
    maintenance
    A Model Context Protocol server that enables interaction with Yahoo Finance to retrieve stock pricing, company information, and historical financial data through natural language queries.
    21
    1,063 PyPI
    28
    MIT

  • MCP Yahoo Finance

    marckwei
    A
    license
    C
    quality
    Not graded
    maintenance
    A Model Context Protocol server that provides tools for interacting with Yahoo Finance, allowing users to retrieve stock prices, company information, and perform financial data comparisons.
    11
    MIT

  • Yahoo Finance MCP Server

    16Coffee
    A
    license
    C
    quality
    D
    maintenance
    A Model Context Protocol server providing comprehensive financial data from Yahoo Finance, allowing users to retrieve detailed stock information, financial statements, options data, and market news.
    34
    MIT

Appeared in Searches