Do I need API keys to use Crypto Market Data?
For local stdio mode, no API keys are needed. For HTTP mode, authentication via API key is required; keys map to tiers (free/pro/ultra) with per-minute and monthly quotas.
@eliasfire617
Basic information
Live crypto market data — price, funding rates, open interest, long/short ratio, order book and candles — across major exchanges, with built-in funding-rate arbitrage comparison.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"crypto-market-data": {
"command": "npx",
"args": [
"-y",
"mcpize",
"run",
"@eliasfire617/crypto-market-data"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Crypto Market Data is a read-only Model Context Protocol (MCP) server that provides AI agents with live cryptocurrency market data from 100+ exchanges via the CCXT library. It uses public endpoints, so no API keys are required for local use. Built for production, it includes retries, timeouts, capability guards, and structured error responses.
You can use it instantly via MCPize (npx -y mcpize connect @eliasfire617/crypto-market-data --client claude) or run locally: install dependencies (pip install -r requirements.txt), then start with python server.py for stdio transport or python server.py --http for HTTP mode. For HTTP, configure API keys via environment variables or a file.
For local stdio mode, no API keys are needed. For HTTP mode, authentication via API key is required; keys map to tiers (free/pro/ultra) with per-minute and monthly quotas.
The server currently supports bybit, binance, okx, hyperliquid, gate, and kucoin. Additional CCXT exchange IDs can be added by modifying `SUPPORTED_EXCHANGES`.
It provides direct, unfiltered market data from public endpoints with robust error handling and caching. The companion server "Crypto Derivatives Intelligence" offers higher-level analysis (funding carry, liquidation zones, regime classification) on top of this data.
You need Python 3 and the CCXT library installed via pip. No external API keys or paid services are required for local operation.
All data is read-only: prices, 24h stats, order books, OHLCV candles, recent trades, funding rates (current & historical), funding rate arbitrage spreads, open interest, long/short ratios, and recent liquidations (limited support).

Banks to AI gives any MCP-compatible agent (Claude, Cursor, or your own) secure, read-only access to real bank data — 12,000+ financial institutions across the US, Canada and beyond. How it works: authenticate via OAuth
Live Proof-of-Work mining data for AI agents: difficulty, hashrate, solo-mining odds, cost of production and hardware profitability for 126+ networks and 770+ ASIC/GPU/CPU models. Read-only, no API key.
Model Context Protocol (MCP) server for 6-protocol DeFi quantitative telemetry, stablecoin carry radar, and risk simulation.

IBANforge — IBAN validation, BIC/SWIFT lookup, Swiss clearing, and EMI/vIBAN classification API with MCP for AI agents

Non-custodial crypto payments for AI agents: checkout sessions, invoices, webhooks and test payments. No KYC.
Comments