Model Context Protocol for Financial Data

Access financial metrics, SEC EDGAR filings, and market data through a clean JSON-RPC interface designed for LLMs.

"My app's AI assistant now fetches latest stock prices for my users and tracks EDGAR filings seamlessly. The JSON-RPC interface is perfect for LLM integration."
— Strategica
{ "jsonrpc": "2.0", "method": "market.getStockPrice", "params": { "symbol": "AAPL", "exchange": "NASDAQ" }, "id": 1 } // Response: { "jsonrpc": "2.0", "result": { "symbol": "AAPL", "price": 178.52, "currency": "USD", "last_updated": "2024-01-15T16:00:00Z" }, "id": 1 }

Try the API Now

Ask questions about financial data and see real API responses using our MCP Financial service

Ask a question about stocks, financial metrics, or market data!

Example: "What's the current price of Apple stock?" or "Calculate the P/E ratio for a stock with price $150 and EPS $5"

Choose Your Plan

Get started with our flexible pricing options designed for developers and enterprises

Free Plan

Perfect for getting started

$0 /month
  • End of day stock prices
  • Basic financial metrics
  • 100 API requests per month
  • Community support
Get Started Free
Most Popular

Pro Plan

For serious financial analysis

$20 /month
  • Everything in Free plan
  • Live stock prices
  • Local MCP Server for Claude Desktop
  • 19+ financial metrics
  • Portfolio optimization
  • 10,000 API requests per month
Get Pro

Business Plan

For enterprise-level analysis

$99 /month
  • Everything in Pro plan
  • 100,000 API requests per month
  • Commodity Prices
  • Commodities History Prices
  • SEC EDGAR Filings API
  • Priority support
Go Business

Key Capabilities

Financial Metrics

Calculate 19+ essential financial ratios and metrics instantly. From P/E ratios to debt-to-equity calculations, get precise financial analysis.

Examples:
  • • Price-to-Earnings (P/E) Ratio
  • • Return on Investment (ROI)
  • • Debt-to-Equity Ratio
  • • Current Ratio & Quick Ratio

SEC EDGAR Filings

Search through millions of SEC documents with AI-powered semantic search. Extract key financial data and insights from 10-K, 10-Q, and 8-K filings.

Use Cases:
  • • Company financial analysis
  • • Risk factor identification
  • • Management discussion extraction
  • • Compliance monitoring

Market Data

Access real-time stock prices, historical data, and market indicators. Build sophisticated trading algorithms and portfolio analysis tools.

Data Sources:
  • • Real-time stock quotes
  • • Historical price data
  • • Market indices (S&P 500, NASDAQ)
  • • Portfolio optimization metrics

LLM-Optimized Interface

Purpose-built for AI agents and language models. Clean JSON-RPC protocol ensures reliable integration with ChatGPT, Claude, and custom AI systems.

AI Integration:
  • • Model Context Protocol (MCP)
  • • Structured JSON responses
  • • Function calling support
  • • Semantic error handling

Developer Experience

Comprehensive documentation, interactive API explorer, and client libraries. Get started in minutes with clear examples and best practices.

Developer Tools:
  • • Interactive API documentation
  • • Python & JavaScript clients
  • • Sandbox environment
  • • Code examples & tutorials

Enterprise Security

Production-ready infrastructure with API key management, rate limiting, and enterprise-grade security. Scale from prototype to production seamlessly.

Security Features:
  • • API key authentication
  • • Rate limiting & quotas
  • • SSL/TLS encryption
  • • Request monitoring & logs

MCP in Action

Example: Calculate Price-to-Earnings Ratio

Request:

{ "jsonrpc": "2.0", "method": "finance.calculateMetric", "params": { "metric_id": "price_to_earnings", "values": { "price": 150.25, "earnings_per_share": 5.30 } }, "id": 1 }

Response:

{ "jsonrpc": "2.0", "result": { "metric_id": "price_to_earnings", "name": "Price-to-Earnings Ratio", "result": 28.35, "formula": "price / earnings_per_share", "parameters": { "price": 150.25, "earnings_per_share": 5.30 }, "interpretation": "The P/E ratio of 28.35 is above average, suggesting investors are expecting higher growth in the future." }, "id": 1 }

Example: Fetch Historical Stock Data

Request:

{ "jsonrpc": "2.0", "method": "marketstack.getHistoricalData", "params": { "symbols": "AAPL", "date_from": "2023-01-01", "date_to": "2023-01-31" }, "id": 2 }

Response:

{ "jsonrpc": "2.0", "result": { "success": true, "data": [ { "date": "2023-01-31", "symbol": "AAPL", "exchange": "XNAS", "open": 142.7, "high": 144.34, "low": 142.28, "close": 144.29, "volume": 86964030 }, /* Additional data points... */ ], "pagination": { "limit": 100, "offset": 0, "total": 21 }, "analysis": { "change": 7.9, "change_percent": 5.8, "average_volume": 92452394 } }, "id": 2 }

Integrate with Your LLM

MCP Financials provides the context layer your LLM needs to deliver accurate financial intelligence.

Integration Example (Python)

import json import requests def call_mcp_financials(method, params): """ Call MCP Financials JSON-RPC API Args: method: The JSON-RPC method name params: The parameters for the method Returns: The API response """ url = "https://mcpfinancials.com/api/jsonrpc" payload = { "jsonrpc": "2.0", "method": method, "params": params, "id": 1 } headers = { "Content-Type": "application/json", "Accept": "application/json" } response = requests.post(url, headers=headers, json=payload) return response.json() # Example: Get list of available financial metrics metrics = call_mcp_financials("discover.getAvailableMetrics", {"category": "valuation"}) print(json.dumps(metrics, indent=2))

Getting Started

1. Explore the Documentation

Browse our comprehensive API documentation to understand all available endpoints and parameters.

Read the Docs →

2. Make Your First API Call

Start with a simple call to test the API:

curl -X POST https://mcpfinancials.com/api/jsonrpc \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "method": "discover.getAvailableMetrics", "params": {}, "id": 1 }'

3. Integrate with Your Application

Use our client libraries or direct API calls to integrate MCP Financials with your application or LLM.