Sponsored by Deepsite.site

CoinGecko API Server MCP

Created By
MCP-Mirror10 months ago
Mirror of
Content

CoinGecko API Server MCP

Version License

A powerful and flexible Node.js Express server that provides a comprehensive interface to the CoinGecko cryptocurrency data API. This server supports both the free public API and the Pro API with automatic fallback.

Quick Start

# Install and run with npx
npx coingecko-api-server

# Or clone and install manually
git clone https://github.com/GaplyDev01/coingecko-api-server.git
cd coingecko-api-server
npm install
npm run setup
npm start

Features

  • 🔄 Dual API Support: Seamlessly works with both CoinGecko Free and Pro APIs
  • 🔙 Automatic Fallback: Falls back to free API during development
  • 🔌 RESTful Endpoints: Simple and intuitive API interface
  • 🛡️ Robust Error Handling: Detailed error messages and proper status codes
  • 🧩 Simple Setup: Quick installation with guided setup
  • 📝 Comprehensive Documentation: Clear usage instructions

Setup Options

This is the fastest way to get started:

npx coingecko-api-server

The interactive setup will:

  1. Ask where to install the server
  2. Clone the repository
  3. Install dependencies
  4. Prompt for your CoinGecko API key (optional)
  5. Configure your server port

Option 2: Manual Setup

If you prefer to set up manually:

# Clone the repository
git clone https://github.com/GaplyDev01/coingecko-api-server.git
cd coingecko-api-server

# Install dependencies
npm install

# Run the setup script
npm run setup

# Start the server
npm start

Configuration

The server can be configured using environment variables in the .env file:

VariableDescriptionDefault
PORTThe port the server will listen on3000
COINGECKO_API_KEYYour CoinGecko Pro API key-

API Endpoints

The server provides access to all essential CoinGecko API endpoints:

Basic Endpoints

  • GET /api/ping - Check CoinGecko API status

Price Data

  • GET /api/simple/price - Get price data for specified coins

    • Query params: ids, vs_currencies, include_market_cap, include_24hr_vol, include_24hr_change, include_last_updated_at, precision
  • GET /api/simple/supported_vs_currencies - Get list of supported vs currencies

Coin Data

  • GET /api/coins/markets - Get market data for coins
    • Query params: vs_currency, ids, category, order, per_page, page, sparkline, price_change_percentage

Market Data

  • GET /api/global - Get global cryptocurrency data
  • GET /api/search/trending - Get trending coins

Full API documentation can be found in the CoinGecko API Documentation.

MCP Integration Information

This is an MCP (Marketplace Component Program) server compatible with AI systems like Claude. To use this server in Claude Desktop:

  1. Start the CoinGecko API server locally
  2. In Claude Desktop, install the MCP by providing the server URL (e.g., http://localhost:3000)
  3. Claude can now access cryptocurrency data through the MCP interface

The server implements the full MCP specification with JSON-RPC 2.0:

  • JSON-RPC 2.0 Endpoint: /rpc - Handles all method calls from AI clients
  • Schema Definition: /mcp/schema - Defines available tools and parameters
  • Standardized Communication: Follows MCP protocol for seamless AI integration

For detailed integration instructions, see MCP_INTEGRATION.md.

Pro API vs Free API

This server supports both the CoinGecko Pro API and the free API:

  • Pro API: Higher rate limits, no throttling, additional endpoints. Requires an API key.
  • Free API: Limited to ~30 calls/minute with potential rate limiting.

The server automatically detects if an API key is provided and uses the appropriate API. If no key is provided, it will fall back to the free API, which is ideal for development or personal use.

For more details about the Pro API setup, see USING_COINGECKO_PRO.md.

Development

# Run in development mode with hot reload
npm run dev

The server uses direct fetch calls to the CoinGecko API, ensuring compatibility with both free and Pro versions.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
ChatWiseThe second fastest AI chatbot™
WindsurfThe new purpose-built IDE to harness magic
Tavily Mcp
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Serper MCP ServerA Serper MCP Server
Amap Maps高德地图官方 MCP Server
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
DeepChatYour AI Partner on Desktop
CursorThe AI Code Editor
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
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。
Playwright McpPlaywright MCP server
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.