Crypto Tracker MCP Server

Crypto Tracker MCP Server

Connects AI agents to real-time cryptocurrency market data from CoinGecko API, enabling price lookups, coin details, market rankings, search, and trending crypto queries through natural language.

Category
访问服务器

README

🪙 Crypto Tracker MCP Server Example

A Model Context Protocol (MCP) server that connects AI agents (like Claude Desktop or other MCP clients) to real-time cryptocurrency market data using the CoinGecko API.

This project demonstrates how to build and run a complete MCP server in Node.js, featuring:

  • 🧰 Tools for interacting with crypto data
  • 📚 (Optional) Resources for reusable info sets
  • 💬 (Optional) Prompt Templates for AI-assisted responses

🚀 Features

Get Real-Time Prices — Fetch live prices, market cap, and 24h change for any cryptocurrency
Detailed Coin Info — Retrieve full metadata for a specific coin
Market Data — Paginated list of coins ranked by market cap
Search Coins — Find coins by name or symbol
Trending Coins — Get currently trending cryptocurrencies on CoinGecko


🧠 What Is MCP?

MCP (Model Context Protocol) is a new open standard that connects Large Language Models (LLMs) to external tools, APIs, and data sources through a single unified interface.

Each MCP Server can expose:

Category Description
🧰 Tools Functions or APIs that an LLM can call (like get_price)
📚 Resources Static or dynamic data references (like coin lists, config files)
💬 Prompt Templates Predefined prompts or instruction templates

Your LLM can then access and execute these capabilities safely and consistently.


🧩 Project Structure


crypto-mcp-server/
├── server.js          # Main MCP server implementation
├── package.json       # Dependencies and module config
└── README.md          # Documentation (this file)


⚙️ Setup

1️⃣ Clone the repository

git clone https://github.com/<your-username>/crypto-mcp-server.git
cd crypto-mcp-server

2️⃣ Install dependencies

npm install

Make sure your package.json includes "type": "module"

3️⃣ Run the server manually

node server.js

You should see:

CoinGecko MCP Server running on stdio

🧩 Integration with Claude Desktop

To connect this MCP server with Claude Desktop, edit your configuration file:

nano ~/Library/Application\ Support/Claude/claude_desktop_config.json

Add the following entry under mcpServers:

{
  "mcpServers": {
    "coingecko": {
      "command": "/Users/<your-username>/.nvm/versions/node/v22.17.1/bin/node",
      "args": ["/Users/<your-username>/work/crypto-mcp-server/server.js"]
    }
  }
}

Then restart Claude Desktop. You’ll now be able to call this server using /mcp commands like:

/mcp coingecko get_price { "ids": "bitcoin", "vs_currencies": "usd" }

🧰 Available Tools

Tool Description Example
get_price Get current price, market cap, and 24h change { "ids": "bitcoin", "vs_currencies": "usd" }
get_coin_details Get metadata about a specific coin { "id": "ethereum" }
get_market_data Paginated market cap data { "vs_currency": "usd", "per_page": 10, "page": 1 }
search_coins Search for cryptocurrencies { "query": "solana" }
get_trending Get trending cryptocurrencies {}

🛠️ Tech Stack

  • Node.js 22+
  • @modelcontextprotocol/sdk
  • CoinGecko REST API
  • ES Modules (import/export syntax)

💡 Future Enhancements

  • Add Resources to store coin metadata or cached lookups
  • Add Prompt Templates for summarizing market trends
  • Add Persistent local caching for performance optimization
  • Integrate with other APIs (Binance, CoinMarketCap, etc.)

🧑‍💻 Author

Saqib Hussain 🚀 Software Engineer | DevOps | AI Integrations 🔗 LinkedIn 🏢 Founder — DevInspect

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选