Independent Reserve MCP Server
Provides real-time cryptocurrency market data from the Independent Reserve exchange, enabling users to query current prices, ticker information, and order book data for various currency pairs through natural language.
README
Independent Reserve MCP Server
This Model Context Protocol (MCP) server provides real-time cryptocurrency data from the Independent Reserve exchange to AI assistants. It allows you to ask questions about cryptocurrency prices and market data.
test
Features
- Real-time Ticker Data: Get the latest price, bid, ask, and volume for any currency pair.
- Real-time Order Book Data: View the current buy and sell orders.
- Automatic Reconnection: The client will automatically reconnect if the connection is lost.
- Easy to Use: Exposes simple tools that an AI can understand.
Project Structure
server.py: The main MCP server that handles tool calls from the AI.ir_client.py: The WebSocket client that connects to the Independent Reserve API and manages data streams.requirements.txt: The Python dependencies for the project..env.example: An example file for configuring your API keys.README.md: This file.
Setup
-
Clone this repository:
git clone <your-repo-url> cd independentreserve-mcp -
Install Python dependencies:
pip install -r requirements.txt -
Configure API Keys (Optional):
- For public data (tickers, order books), no API key is needed.
- If you want to add private data features later (like account balances), create a
.envfile in the project root. - Copy
.env.exampleto.envand fill in your Independent Reserve API keys.Then editcp .env.example .env.envwith your credentials.
Usage
Once the server is running, you can ask questions like:
- "What is the current price of Bitcoin in USD?"
- "Show me the order book for ETH/AUD."
The server provides the following tools:
get_ticker(primary_currency, secondary_currency): Gets the latest ticker information.get_order_book(primary_currency, secondary_currency): Gets the latest order book data.
Connecting to Claude Desktop
To use this server with Claude Desktop, you need to add it to your Claude configuration file.
-
Find your Claude Desktop config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
-
Add the server configuration: Open the file and add the following
mcpServersobject. Make sure to replace/path/to/your/independentreserve-mcpwith the absolute path to the project folder on your computer.{ "mcpServers": { "independentreserve": { "command": "python", "args": [ "/path/to/your/independentreserve-mcp/server.py" ], "env": { "IR_API_KEY": "your_api_key_if_needed", "IR_API_SECRET": "your_api_secret_if_needed" } } } } -
Restart Claude Desktop. After restarting, Claude will automatically connect to your new MCP server. You can now start asking it about cryptocurrency prices from Independent Reserve!
Next Steps and Improvements
- Authentication: Implement the signed message logic to subscribe to private channels like balance, orders, and trades. This would require adding new tools like
get_my_balance. - Smarter Subscriptions: Instead of subscribing every time a tool is called, the client could be smarter. For example, if the AI asks for the BTC/USD ticker, it could stay subscribed to it for a few minutes in case of follow-up questions.
- Error Handling: Add more robust error handling for invalid currency pairs or API errors.
- More Data: Add a tool for
get_recent_trades.
Disclaimer
This project is for educational purposes only. It is not intended to be used for financial advice.
推荐服务器
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 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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。