Toolstem MCP Server
Servidor MCP Toolstem
Herramientas de inteligencia financiera listas para agentes: seleccionadas, no en bruto.
Toolstem es un servidor MCP (Model Context Protocol) que convierte datos brutos del mercado financiero en inteligencia sintetizada y seleccionada para agentes de IA. A diferencia de los envoltorios de paso que solo exponen una API REST de un proveedor, cada herramienta de Toolstem combina múltiples fuentes de datos, deriva señales y precalcula las matemáticas que un agente tendría que hacer por sí mismo.
Una llamada. Una respuesta JSON amigable para el agente. Sin arrays anidados que analizar, sin unir puntos finales, sin código repetitivo de comprobación de nulos.
¿Por qué Toolstem?
La mayoría de los servidores MCP financieros exponen una herramienta por punto final de API, lo que obliga a su agente a realizar 4-5 llamadas secuenciales, escribir código de unión y razonar sobre formas de datos sin procesar. Toolstem está construido de manera diferente:
Obtención de datos en paralelo — cada herramienta se despliega a múltiples fuentes simultáneamente.
Señales derivadas — recomendaciones legibles por humanos como
UNDERVALUED,STRONG,ACCELERATINGcalculadas a partir de números brutos.Matemáticas precalculadas — CAGR, crecimiento interanual (YoY), tendencias de margen, distancia desde el máximo/mínimo de 52 semanas, rendimiento de FCF y más ya están en la respuesta.
Esquema plano y predecible — sin peculiaridades de proveedores profundamente anidadas que se filtren en los prompts del agente.
Degradación elegante — si un punto final ascendente falla, el resto de la respuesta sigue llegando con nulos en su lugar.
Related MCP server: Financial Modeling Prep MCP Server
Herramientas
get_stock_snapshot
Resumen completo de acciones que combina cotización, perfil, valoración DCF y calificación en una sola respuesta.
Entrada:
{
"symbol": "AAPL"
}Ejemplo de salida (truncado):
{
"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"
}
}Campos derivados (no en APIs crudas):
dcf_signal—UNDERVALUEDsi el alza del DCF > 10%,OVERVALUEDsi < -10%, de lo contrarioFAIRLY VALUED.market_cap_readable— formato amigable para humanos$2.78T,$450.2B,$12.5M.distance_from_52w_high_percent/distance_from_52w_low_percent— posición de rango precalculada.
get_company_metrics
Análisis profundo de fundamentos — rentabilidad, salud financiera, flujo de caja, crecimiento y métricas por acción — sintetizado a partir de 5 puntos finales de estados financieros.
Entrada:
{
"symbol": "AAPL",
"period": "annual"
}period acepta annual (predeterminado) o quarter.
Ejemplo de salida (truncado):
{
"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"
}
}Campos derivados:
margin_trend—EXPANDING,STABLEoCONTRACTINGbasado en la dirección de la serie de margen neto.health_signal—STRONG,ADEQUATEoWEAKa partir de la relación deuda-capital, ratio actual y cobertura de intereses.growth_signal—ACCELERATING,STEADYoDECELERATINGbasado en la trayectoria de crecimiento interanual.revenue_cagr,net_income_cagr,fcf_cagr— tasas de crecimiento anual compuesto durante el período analizado.fcf_margin,fcf_yield— precalculados a partir de flujo de caja + ingresos + capitalización de mercado.
Instalación
npm
npm install -g toolstem-mcp-serverEjecutar como servidor stdio:
FMP_API_KEY=your_key_here toolstem-mcp-serverEjecutar como servidor HTTP (transporte HTTP transmitible):
FMP_API_KEY=your_key_here PORT=3000 toolstem-mcp-server --httpClaude Desktop
Añadir a su claude_desktop_config.json:
{
"mcpServers": {
"toolstem": {
"command": "npx",
"args": ["-y", "toolstem-mcp-server"],
"env": {
"FMP_API_KEY": "your_fmp_api_key"
}
}
}
}Smithery
Toolstem se distribuye en Smithery para una instalación con un solo clic en clientes MCP compatibles.
Apify
Disponible en la tienda de Apify como el Actor toolstem-financial-data. Llámelo desde su flujo de trabajo de Apify con la entrada:
{
"tool": "get_stock_snapshot",
"symbol": "AAPL"
}o
{
"tool": "get_company_metrics",
"symbol": "AAPL",
"period": "annual"
}Los resultados se envían al conjunto de datos predeterminado. El actor monetiza por llamada de herramienta a través del modelo de pago por evento de Apify.
Autoalojamiento (Cloudflare Workers / cualquier entorno de ejecución Node)
Construya y ejecute el transporte HTTP:
npm install
npm run build
FMP_API_KEY=your_key npm run start:httpSu cliente MCP puede entonces conectarse a POST http://your-host:3000/mcp.
Variables de entorno
Variable | Requerido | Descripción |
| Sí | Clave de API de Financial Modeling Prep. Obtenga una en financialmodelingprep.com. |
| No | Puerto para transporte HTTP. El valor predeterminado es |
Desarrollo
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 serverArquitectura
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 signalsTodos los puntos finales de FMP están envueltos en una única clase FmpClient. Las implementaciones de herramientas se despliegan a múltiples métodos de cliente en paralelo a través de Promise.all, y luego sintetizan el resultado fusionado.
Licencia
MIT — ver LICENSE.
Toolstem — inteligencia financiera seleccionada para la economía nativa de agentes.
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