mcpField
F
FinData MCP

FinData MCP

Local
github.com/sapph1reFinance1Updated 12w ago

About FinData MCP

FinData MCP is a financial data server for AI agents, offering stock and crypto prices, company fundamentals, FRED indicators, and SEC filings. It combines five query tools with per-call x402 payments on Base.

Key features

  1. 01Stock quotes and company fundamentals
  2. 02800,000+ FRED economic series
  3. 03SEC EDGAR filings
  4. 04Cryptocurrency prices
  5. 05x402 payments per call

Use cases

  1. 01Check stock prices and company metrics
  2. 02Review macroeconomic indicators
  3. 03Retrieve SEC filings
  4. 04Look up cryptocurrency prices

MCP support

The MCP server exposes five financial data tools to MCP clients: stock quotes, company fundamentals, economic indicators, SEC filings, and crypto prices. Calls are paid through x402 micropayments on Base.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"findata": {
"command": "uvx",
"args": [
"findata-mcp"
],
"env": {
"EVM_PRIVATE_KEY": "<EVM_PRIVATE_KEY>",
"FINDATA_BACKEND_URL": "<FINDATA_BACKEND_URL>"
}
}
}
}
Run commanduvx findata-mcp
Environment variables to set
EVM_PRIVATE_KEYSecretEVM wallet private key (hex, with or without 0x prefix). Any EVM wallet with USDC on Base mainnet. Used for x402 micropayments ($0.01/call).
FINDATA_BACKEND_URLOverride the default backend URL. Defaults to https://findata-mcp-production-1cd3.up.railway.app

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypifindata-mcp0.3.3

Tools

5

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
symbolstringNoAlias for ticker — use either ticker or symbol
tickerstringNoStock ticker symbol (e.g. AAPL, TSLA, MSFT, NVDA)

Details

From the project README

FinData MCP

MCP.Directory

Stock market data, company fundamentals, FRED macroeconomic indicators, SEC EDGAR filings, and cryptocurrency prices for AI agents — all in one MCP server. Free trial: 50 calls/day. Pay-per-use: $0.01/call via x402 micropayments on Base. No signup, no API key.

Financial data for AI agents. Five tools covering real-time stock prices (NYSE, NASDAQ, 50,000+ tickers), equity fundamentals (P/E ratio, earnings, market cap), 800,000+ FRED economic series (GDP, CPI, inflation, interest rates, Treasury yields), SEC EDGAR filings (10-K annual reports, 10-Q, 8-K), and crypto prices (Bitcoin, Ethereum, 8,000+ coins). Works with Claude Desktop, Cursor, Windsurf, and any MCP client.

Quick Start

Install:

pip install findata-mcp

Set your wallet key (any EVM wallet with USDC on Base):

export EVM_PRIVATE_KEY=your_private_key_here

Add to Claude Desktop — edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "findata-mcp": {
      "command": "findata-mcp",
      "env": {
        "EVM_PRIVATE_KEY": "your_private_key_here"
      }
    }
  }
}

Add to Cursor — edit .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "findata-mcp": {
      "command": "findata-mcp",
      "env": {
        "EVM_PRIVATE_KEY": "your_private_key_here"
      }
    }
  }
}

Restart your client. You now have five financial data tools available.


Tools

ToolWhat it returnsCache
stock_quote(ticker)Price, volume, change %, market cap1 min
company_fundamentals(ticker)Revenue, P/E, sector, beta, dividend yield, description1 hr
economic_indicator(series_id)800,000+ FRED series (GDP, CPI, rates, yield curves)6 hr
sec_filing(ticker, form_type)Full text of 10-K, 10-Q, 8-K from SEC EDGAR24 hr
crypto_price(coin_id)Price, market cap, 24h volume, 7-day sparkline1 min

Examples

Get a stock quote
stock_quote(ticker="NVDA")
{
  "ticker": "NVDA",
  "price": 878.35,
  "change": 12.40,
  "change_pct": 1.43,
  "volume": 41200000,
  "market_cap": 2150000000000,
  "currency": "USD"
}
Look up company fundamentals
company_fundamentals(ticker="AAPL")
{
  "ticker": "AAPL",
  "name": "Apple Inc.",
  "sector": "Technology",
  "market_cap": 3280000000000,
  "pe_ratio": 33.2,
  "revenue": 383285000000,
  "beta": 1.24,
  "dividend_yield": 0.0044
}
Check an economic indicator
economic_indicator(series_id="FEDFUNDS")
{
  "series_id": "FEDFUNDS",
  "title": "Federal Funds Effective Rate",
  "units": "Percent",
  "frequency": "Monthly",
  "latest_value": 4.33,
  "latest_date": "2026-02-01"
}

Common FRED series: GDP, CPIAUCSL (inflation), UNRATE (unemployment), DGS10 (10-year Treasury), FEDFUNDS.

Read an SEC filing
sec_filing(ticker="AAPL", form_type="10-K")
{
  "ticker_or_cik": "AAPL",
  "form_type": "10-K",
  "filing_date": "2025-11-01",
  "document_url": "https://www.sec.gov/Archives/...",
  "content": "UNITED STATES SECURITIES AND EXCHANGE COMMISSION..."
}

Also accepts ticker_or_cik (legacy) or symbol as aliases for ticker.


Pricing

$0.01 per call. No signup, no API keys, no monthly fees.

Payment happens automatically via x402 — an open micropayment protocol. Your MCP client signs a USDC transfer on Base mainnet for each call. You need:

  1. An EVM wallet private key (set as EVM_PRIVATE_KEY)
  2. A small USDC balance on Base mainnet (~$1 covers 100 calls)

That's it. No accounts, no rate limits, no billing pages.


How It Works

The pip install package is a thin MCP stdio server. It proxies your tool calls to a hosted backend, automatically handling x402 payment signing. Data comes from Yahoo Finance, FRED, SEC EDGAR, and CoinGecko.

Your AI agent  →  findata-mcp (local stdio)  →  Backend (Railway)  →  Data providers
                  signs x402 payment              verifies payment

Configuration

VariableRequiredDefaultDescription
EVM_PRIVATE_KEYYes—Wallet private key with USDC on Base
FINDATA_BACKEND_URLNoProduction URLOverride for self-hosted backend

Alternative Install Methods

uvx (no install needed):

uvx findata-mcp

Distribution Status

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.