What dependencies are required?
Python 3.9 or higher, the `mcp` SDK, and the `ccxt` library. Install them via `pip` or `uv`.
@MCP-Mirror
基本信息
Mirror of
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"Nayshins_mcp-server-ccxt": {
"command": "uv",
"args": [
"pip",
"install",
"mcp",
"ccxt"
]
}
}
}"What's the current price of BTC/USDT on Binance?"
"Show me a market summary for ETH/USDT"
"What are the top 5 trading pairs on Kraken?"
"Which exchanges are supported?"
"Show me the last 7 days of BTC/USDT price data in 1-hour intervals"
"What's the 24-hour price change for SOL/USDT?"
"Show me the trading volume history for ETH/USDT over the last week"
A Model Context Protocol (MCP) server that provides real-time and historical cryptocurrency market data through integration with major exchanges, enabling LLMs like Claude to fetch current prices, analyze market trends, and access detailed trading information.
Install mcp and ccxt via uv pip install mcp ccxt or pip install mcp ccxt, then run python crypto_server.py. Configure Claude Desktop by adding the server to claude_desktop_config.json with the command and path to the script. Once connected, use built-in tools such as get-price, get-market-summary, get-top-volumes, list-exchanges, get-historical-ohlcv, get-price-change, and get-volume-history via natural language queries.
Python 3.9 or higher, the `mcp` SDK, and the `ccxt` library. Install them via `pip` or `uv`.
The server implements error handling for rate limits; users can also add delays between requests or switch exchanges to avoid hitting limits.
Check your internet connection, verify the exchange is operational, and ensure the trading pair exists on the selected exchange.
No—the server uses CCXT’s public endpoints and does not require user API keys for the tools listed.
Data is fetched live from the supported exchanges via the CCXT library; no local caching or storage is mentioned.

Ask your AI about any land in Tamil Nadu. 100+ checks over the state's government registers: who owns a survey number, guideline value, encumbrance (EC), FMB sketch, coastal and zoning checks, road width, stamp duty and

AI visibility analytics across 15+ providers (ChatGPT, Perplexity, Gemini, AI Overviews, and more). The MCP connector lets assistants run scans, compare competitor mentions, and track your brand's visibility in AI answer

Ask your website analytics in plain language and set up funnels, features and dashboards. Cookieless, with one-step undo.

Session replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can
Verify scraped data against the live source page. Signed verdicts, $0.01 via x402.
评论