mcpField
C
Crypto Market Data

Crypto Market Data

Local
github.com/eliasfire617Finance2Updated 20w ago

About Crypto Market Data

Crypto Market Data is a read-only MCP server that gives AI agents live cryptocurrency data across exchanges via CCXT. It covers spot and derivatives data and compares annualized funding rates across venues.

Key features

  1. 01Retrieve prices, candles, and order books
  2. 02Get current and historical funding rates
  3. 03Compare funding rates across exchanges
  4. 04Query open interest and long/short ratios
  5. 05Discover exchanges, capabilities, and symbols

Use cases

  1. 01Monitor crypto markets across exchanges
  2. 02Compare perpetual funding-rate differences
  3. 03Inspect order books and recent trades for a symbol

MCP support

The read-only MCP server exposes 13 market-data tools to AI clients, using public endpoints from supported exchanges. It supports local stdio connections and HTTP mode with authentication and rate limits.

Configuration

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

mcp.json · Universal config
{
"mcpServers": {
"crypto-market-data": {
"command": "npx",
"args": [
"-y",
"mcpize"
]
}
}
}
Run commandnpx -y mcpize

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
npmmcpize

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Crypto Market Data MCP Server

MCPize

A read-only Model Context Protocol server that gives any AI agent (Claude, Cursor, Cline, Windsurf…) live cryptocurrency market data across 100+ exchanges via CCXT. No API keys required — everything uses public endpoints.

Supported exchanges: bybit, binance, okx, hyperliquid, gate, kucoin (add more CCXT ids in SUPPORTED_EXCHANGES).

Connect via MCPize

Use this MCP server instantly with no local installation:

npx -y mcpize connect @eliasfire617/crypto-market-data --client claude

Or connect at: https://mcpize.com/mcp/crypto-market-data

Tools (13)

Discovery

ToolWhat it does
list_exchangesWhich exchanges are supported
get_capabilitiesMatrix of which exchange supports which data (no network)
search_symbolsFind the exact symbol format for a coin

Market data

ToolWhat it does
get_priceLast price + 24h stats
get_order_bookTop-of-book bids/asks
get_ohlcvRecent OHLCV candles
get_recent_tradesLatest public trades

Derivatives

ToolWhat it does
get_funding_rateCurrent perpetual funding rate
get_funding_rate_historyHistorical funding rates
compare_fundingFunding rate across many exchanges + arb spread
get_open_interestCurrent open interest
get_long_short_ratioGlobal long/short account ratio (Binance)
get_liquidationsRecent public liquidations (limited support)

compare_funding is the differentiator: it surfaces funding-rate arbitrage opportunities (which venue pays the most vs least) in one concurrent call. Rates are annualized (apr_pct) before comparing — venues fund at different cadences (Hyperliquid hourly vs 8h elsewhere), so raw rates aren't comparable.

Want the analysis, not just the data? The companion server Crypto Derivatives Intelligence builds on this data: funding-carry opportunities netted of fees (breakeven days, executable depth), OI-price divergence, liquidation zones, positioning extremes, and market-regime classification — one tool call each.

Robustness

Built for production, not a demo:

  • Retries with exponential backoff on transient network errors (3 attempts).
  • Per-request + overall timeouts (10s / 25s) so a hung exchange can't stall a call.
  • Capability guards: never calls a method an exchange lacks — returns a clean error listing which exchanges do support it (see get_capabilities).
  • Structured errors ({"error": {type, message, retryable, supported_exchanges}}) instead of crashes — agents always get a parseable response.
  • TTL response cache (~660x faster on repeat calls; eases rate limits).
  • Input validation and clamped limits on every tool.
  • Guaranteed exchange cleanup; logs to stderr only (safe for stdio transport).

Run locally

python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# stdio transport (Claude Desktop, Cursor, Cline) — local, no auth:
python server.py

# OR streamable HTTP (hosted / remote) — API-key auth + rate limiting ON:
python server.py --http                 # binds :8000 (override with PORT=8799)

Authentication & billing (HTTP mode)

The hosted HTTP transport is gated — this is what makes it billable. Local stdio stays open for single-user dev.

  • Clients send Authorization: Bearer <api-key>.

  • Each key maps to a client_id and a tier; unknown/missing keys get 401.

  • Tiers (auth.py → TIERS) set per-minute rate + monthly quota:

    Tierreq/minmonthly quota
    free101,000
    pro120100,000
    ultra6002,000,000
  • Over the limit → a clean ToolError (Rate limit exceeded… / Monthly quota exceeded…), never a crash.

Configure keys (either source; file wins):

# inline
export CRYPTO_MCP_API_KEYS="sk_live_abc:acme:pro,sk_live_xyz:jane:free"
# or a file (see api_keys.example.json)
export CRYPTO_MCP_API_KEYS_FILE=./api_keys.json

If no keys are set in HTTP mode, a throwaway demo key (tier=pro) is generated and printed to stderr so you can test immediately.

Behind a gateway (e.g. MCPize)

If you deploy behind a platform that already authenticates and rate-limits subscribers, set CRYPTO_MCP_DISABLE_AUTH=1. The server then trusts the gateway and skips its own auth + rate limiting — no double authentication, no double throttling. Only do this when the container is reachable solely through that gateway.

Use with Claude Desktop

Copy claude_desktop_config.example.json into your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows), adjusting paths.

Symbols
  • Spot: BTC/USDT
  • Perpetual: BTC/USDT:USDT
  • Common shorthand is normalized automatically: btc, BTCUSDT, BTC-USDT all work (funding/OI tools land on the perp form).

Roadmap

  • Add more exchanges to SUPPORTED_EXCHANGES.
  • More aggressive caching of hot symbols to cut latency.
  • Optional websocket streaming for live order book / trades.

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.