Toolstem MCP Server
Toolstem MCP-Server
Agent-fähige Finanzintelligenz-Tools — kuratiert, nicht roh.
Toolstem ist ein MCP-Server (Model Context Protocol), der rohe Finanzmarktdaten in kuratierte, synthetisierte Intelligenz für KI-Agenten umwandelt. Im Gegensatz zu einfachen Wrappern, die lediglich die REST-API eines Anbieters bereitstellen, kombiniert jedes Tool von Toolstem mehrere Datenquellen, leitet Signale ab und führt die Berechnungen vorab durch, die ein Agent sonst selbst erledigen müsste.
Ein Aufruf. Eine agentenfreundliche JSON-Antwort. Keine verschachtelten Arrays zum Parsen, kein Zusammenfügen von Endpunkten, kein Boilerplate-Code für Null-Prüfungen.
Warum Toolstem?
Die meisten Finanz-MCP-Server stellen ein Tool pro API-Endpunkt bereit – was Ihren Agenten dazu zwingt, 4–5 sequentielle Aufrufe zu tätigen, Klebecode zu schreiben und über rohe Datenstrukturen nachzudenken. Toolstem ist anders aufgebaut:
Paralleles Datenabrufen — jedes Tool greift gleichzeitig auf mehrere Quellen zu.
Abgeleitete Signale — für Menschen lesbare Empfehlungen wie
UNDERVALUED,STRONG,ACCELERATING, die aus Rohzahlen berechnet werden.Vorab berechnete Mathematik — CAGRs, YoY-Wachstum, Margentrends, Abstand zum 52-Wochen-Hoch/-Tief, FCF-Rendite und mehr sind bereits in der Antwort enthalten.
Flaches, vorhersehbares Schema — keine tief verschachtelten Anbieter-Eigenheiten, die in Agenten-Prompts durchsickern.
Graceful Degradation — wenn ein Upstream-Endpunkt ausfällt, wird der Rest der Antwort weiterhin mit Null-Werten an den entsprechenden Stellen geliefert.
Related MCP server: Financial Modeling Prep MCP Server
Tools
get_stock_snapshot
Umfassender Aktienüberblick, der Kurs, Profil, DCF-Bewertung und Rating in einer einzigen Antwort kombiniert.
Eingabe:
{
"symbol": "AAPL"
}Beispielausgabe (gekürzt):
{
"symbol": "AAPL",
"company_name": "Apple Inc.",
"sector": "Technology",
"industry": "Consumer Electronics",
"exchange": "NASDAQ",
"price": {
"current": 178.52,
"change": 2.34,
"change_percent": 1.33,
"day_high": 179.80,
"day_low": 175.10,
"year_high": 199.62,
"year_low": 130.20,
"distance_from_52w_high_percent": -10.57,
"distance_from_52w_low_percent": 37.11
},
"valuation": {
"market_cap": 2780000000000,
"market_cap_readable": "$2.78T",
"pe_ratio": 29.5,
"dcf_value": 195.20,
"dcf_upside_percent": 9.35,
"dcf_signal": "FAIRLY VALUED"
},
"rating": {
"score": 4,
"recommendation": "Buy",
"dcf_score": 5,
"roe_score": 4,
"roa_score": 4,
"de_score": 5,
"pe_score": 3
},
"fundamentals_summary": {
"beta": 1.28,
"avg_volume": 55000000,
"employees": 164000,
"ipo_date": "1980-12-12",
"description": "Apple Inc. designs, manufactures..."
},
"meta": {
"source": "Toolstem via Financial Modeling Prep",
"timestamp": "2026-04-17T18:30:00Z",
"data_delay": "End of day"
}
}Abgeleitete Felder (nicht in rohen APIs enthalten):
dcf_signal—UNDERVALUED, wenn DCF-Aufwärtspotenzial > 10 %,OVERVALUED, wenn < -10 %, sonstFAIRLY VALUED.market_cap_readable— menschenfreundliches Format wie$2.78T,$450.2B,$12.5M.distance_from_52w_high_percent/distance_from_52w_low_percent— vorab berechnete Position im Bereich.
get_company_metrics
Tiefgehende Fundamentalanalyse — Rentabilität, finanzielle Gesundheit, Cashflow, Wachstum und Kennzahlen pro Aktie — synthetisiert aus 5 Finanzbericht-Endpunkten.
Eingabe:
{
"symbol": "AAPL",
"period": "annual"
}period akzeptiert annual (Standard) oder quarter.
Beispielausgabe (gekürzt):
{
"symbol": "AAPL",
"period": "annual",
"latest_period_date": "2025-09-30",
"profitability": {
"revenue": 394328000000,
"revenue_readable": "$394.3B",
"revenue_growth_yoy": 7.8,
"net_income": 96995000000,
"net_income_readable": "$97.0B",
"gross_margin": 46.2,
"operating_margin": 31.5,
"net_margin": 24.6,
"roe": 160.5,
"roa": 28.3,
"roic": 56.2,
"margin_trend": "EXPANDING"
},
"financial_health": {
"total_debt": 111000000000,
"total_cash": 65000000000,
"net_debt": 46000000000,
"debt_to_equity": 1.87,
"current_ratio": 1.07,
"interest_coverage": 41.2,
"health_signal": "STRONG"
},
"cash_flow": {
"operating_cash_flow": 118000000000,
"free_cash_flow": 104000000000,
"free_cash_flow_readable": "$104.0B",
"fcf_margin": 26.4,
"capex": 14000000000,
"dividends_paid": 15000000000,
"buybacks": 89000000000,
"fcf_yield": 3.7
},
"growth_3yr": {
"revenue_cagr": 8.2,
"net_income_cagr": 10.1,
"fcf_cagr": 9.5,
"growth_signal": "ACCELERATING"
},
"per_share": {
"eps": 6.42,
"book_value_per_share": 3.99,
"fcf_per_share": 6.89,
"dividend_per_share": 0.96,
"payout_ratio": 14.9
},
"meta": {
"source": "Toolstem via Financial Modeling Prep",
"timestamp": "2026-04-17T18:30:00Z",
"periods_analyzed": 3,
"data_delay": "End of day"
}
}Abgeleitete Felder:
margin_trend—EXPANDING,STABLEoderCONTRACTINGbasierend auf der Richtung der Nettomargen-Reihe.health_signal—STRONG,ADEQUATEoderWEAKbasierend auf Verschuldungsgrad, Liquiditätsgrad und Zinsdeckungsquote.growth_signal—ACCELERATING,STEADYoderDECELERATINGbasierend auf der YoY-Wachstumstrajektorie.revenue_cagr,net_income_cagr,fcf_cagr— durchschnittliche jährliche Wachstumsraten über den analysierten Zeitraum.fcf_margin,fcf_yield— vorab berechnet aus Cashflow + Umsatz + Marktkapitalisierung.
Installation
npm
npm install -g toolstem-mcp-serverAusführung als stdio-Server:
FMP_API_KEY=your_key_here toolstem-mcp-serverAusführung als HTTP-Server (Streamable HTTP Transport):
FMP_API_KEY=your_key_here PORT=3000 toolstem-mcp-server --httpClaude Desktop
Hinzufügen zu Ihrer claude_desktop_config.json:
{
"mcpServers": {
"toolstem": {
"command": "npx",
"args": ["-y", "toolstem-mcp-server"],
"env": {
"FMP_API_KEY": "your_fmp_api_key"
}
}
}
}Smithery
Toolstem wird auf Smithery für die Ein-Klick-Installation in unterstützten MCP-Clients bereitgestellt.
Apify
Verfügbar im Apify Store als toolstem-financial-data Actor. Rufen Sie ihn aus Ihrem Apify-Workflow mit folgender Eingabe auf:
{
"tool": "get_stock_snapshot",
"symbol": "AAPL"
}oder
{
"tool": "get_company_metrics",
"symbol": "AAPL",
"period": "annual"
}Die Ergebnisse werden in das Standard-Dataset übertragen. Der Actor monetarisiert pro Tool-Aufruf über das Pay-Per-Event-Modell von Apify.
Self-Hosting (Cloudflare Workers / jede Node-Laufzeitumgebung)
Erstellen und Ausführen des HTTP-Transports:
npm install
npm run build
FMP_API_KEY=your_key npm run start:httpIhr MCP-Client kann sich dann mit POST http://your-host:3000/mcp verbinden.
Umgebungsvariablen
Variable | Erforderlich | Beschreibung |
| Ja | Financial Modeling Prep API-Schlüssel. Erhältlich unter financialmodelingprep.com. |
| Nein | Port für den HTTP-Transport. Standard ist |
Entwicklung
npm install
npm run dev # stdio, hot reload via tsx
npm run build # TypeScript -> dist/
npm start # run built stdio server
npm run start:http # run built HTTP serverArchitektur
src/
├── index.ts # MCP server entry (stdio + Streamable HTTP)
├── actor.ts # Apify Actor entry
├── services/
│ └── fmp.ts # Financial Modeling Prep API client
├── tools/
│ ├── get-stock-snapshot.ts
│ └── get-company-metrics.ts
└── utils/
└── formatting.ts # Market cap formatting, CAGR, trend signalsAlle FMP-Endpunkte sind in einer einzigen FmpClient-Klasse gekapselt. Tool-Implementierungen greifen parallel über Promise.all auf mehrere Client-Methoden zu und synthetisieren dann das zusammengeführte Ergebnis.
Lizenz
MIT — siehe LICENSE.
Toolstem — kuratierte Finanzintelligenz für die Agenten-native Wirtschaft.
Available Tools
3 toolscompare_companiesCompany ComparisonARead-onlyIdempotent
Side-by-side comparison of 2-5 companies across price, valuation (P/E, P/B, P/S, EV/EBITDA, DCF), profitability (margins, ROE, ROA, ROIC), financial health (D/E, current ratio, interest coverage), growth (revenue and earnings YoY), dividends, and analyst ratings. Returns derived rankings showing which company leads each dimension — lowest_pe, highest_margin, strongest_balance_sheet, best_growth, most_undervalued, highest_rated. Use this for investment comparisons, competitive analysis, or evaluating alternatives in the same sector.
Inputs: symbols (required). Returns: symbols_compared, comparison_date, companies, rankings, +1 more
get_company_metricsCompany MetricsARead-onlyIdempotent
Deep financial analysis including profitability, financial health, cash flow, growth (3-year CAGR), and per-share metrics. Synthesizes key metrics, financial ratios, income statement, balance sheet, and cash flow statement into one agent-ready response with derived signals: margin_trend (EXPANDING/STABLE/CONTRACTING), health_signal (STRONG/ADEQUATE/WEAK), and growth_signal (ACCELERATING/STEADY/DECELERATING). Use this for fundamental analysis, financial health checks, or when you need to understand a company's trajectory.
Inputs: symbol (required), period. Returns: symbol, period, latest_period_date, profitability, +5 more
get_stock_snapshotStock SnapshotARead-onlyIdempotent
Get a comprehensive stock snapshot including real-time price, valuation metrics, DCF analysis, and analyst ratings for any publicly traded company. Returns curated, agent-ready data synthesized from multiple sources in a single call — includes derived signals like dcf_signal (UNDERVALUED/FAIRLY VALUED/OVERVALUED), human-readable market cap, and 52-week range distance. Use this when you need a quick overview of a stock before digging into financials.
Inputs: symbol (required). Returns: symbol, company_name, sector, industry, +6 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The three tools are largely distinct: snapshot gives a quick overview, company_metrics provides deep financials, and compare_companies does side-by-side analysis. However, get_stock_snapshot and get_company_metrics both include valuation and financial data, so an agent could occasionally hesitate on which to call first.
All tool names follow a clear verb_noun pattern: get_stock_snapshot, get_company_metrics, compare_companies. The verb changes appropriately for the action, and there is no mixing of styles or vague naming.
Three tools is on the lean side but fits a focused stock-analysis server: overview, deep dive, and comparison. Each tool earns its place and the count feels sufficient rather than bloated.
The surface covers the core workflow: quick overview, fundamental analysis, and comparative screening. Minor gaps exist (e.g., no historical price data or explicit ticker search), but agents can accomplish most typical investment-analysis tasks without dead ends.
Maintenance
Related MCP Connectors
SEC filings and financial data for AI agents: 59 tools for statements, valuation and supply chains.
Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.
13-model stock valuation engine for AI agents - fair values for 5,900+ US stocks, updated daily.
Live crypto + IDX stock market intelligence for AI agents — 19 tools, no API key.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to access and analyze financial data, stock information, company fundamentals, and market insights through 250+ tools covering stocks, ETFs, crypto, forex, commodities, and economics.624 npmApache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to access and analyze financial data such as stocks, ETFs, crypto, forex, commodities, company fundamentals, financial statements, and market insights through 250+ configurable tools.624 npmApache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to access and analyze financial data through 250+ tools covering stocks, ETFs, crypto, forex, commodities, economics, company fundamentals, statements, metrics, technical indicators, quotes, news, SEC filings, and more. Supports dynamic, static, or full tool loading for flexible integration.624 npmApache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to access and analyze financial data, stock information, company fundamentals, and market insights through 250+ tools covering stocks, ETFs, crypto, forex, commodities, and economics.624 npmApache 2.0