Deribit MCP Server
Enables real-time cryptocurrency price monitoring and intelligent alerts for Deribit exchange through Claude Desktop. Set price alerts using natural language and receive instant Telegram notifications when conditions are met.
README
Deribit MCP Server
A Model Context Protocol (MCP) server that integrates with the Deribit cryptocurrency exchange, providing real-time price monitoring and intelligent alerts through Claude Desktop.
📱 Multiple Messaging Options Available:
- This README: Telegram integration (with text messages AND phone calls with TTS)
- Signal Integration: Signal Messenger integration (privacy-focused, text messages only)
Both can run simultaneously! Choose based on your preferred messaging platform.
Overview
This MCP server enables Claude to monitor cryptocurrency prices on Deribit and send you instant Telegram notifications when price conditions are met. Set alerts for BTC, ETH, and other instruments using natural language in Claude Desktop.
Key Capabilities:
- 🔔 Smart Price Alerts: Set alerts using conditions like "above", "below", "crosses above/below", or "percentage change"
- 📱 Telegram Notifications: Receive instant alerts on your phone via Telegram
- 📊 Real-time Data: WebSocket connections for live price feeds
- 💼 Account Management: View balances, positions, and account summaries
- 🔄 Live Monitoring: Continuous price tracking with automatic alert triggering
Quick Start
-
Install dependencies:
python3 -m venv venv && source venv/bin/activate pip3 install -e . -
Get Telegram credentials:
- Create a bot: Message @BotFather, send
/newbot - Get chat ID: Message @userinfobot
Optional - For Phone Call Alerts:
- Authorize CallMeBot: Visit https://api2.callmebot.com/txt/auth.php
- Note your exact Telegram username (e.g.,
@yourname) from Settings → Edit Profile
- Create a bot: Message @BotFather, send
-
Configure Claude Desktop: Edit
~/Library/Application Support/Claude/claude_desktop_config.json:{ "mcpServers": { "deribit": { "command": "/path/to/mcp-server/venv/bin/python", "args": ["-m", "src.server"], "cwd": "/path/to/mcp-server", "env": { "DERIBIT_TEST_MODE": "true", "TELEGRAM_BOT_TOKEN": "your_bot_token", "TELEGRAM_CHAT_ID": "your_chat_id", "CALLMEBOT_USERNAME": "@yourname" } } } }Note:
CALLMEBOT_USERNAMEis optional - only needed for phone call alerts -
Restart Claude Desktop and try:
"Set an alert for BTC-PERPETUAL when it goes above $100,000"
Features
- Real-time Price Monitoring: WebSocket connection for live price feeds
- Price Alerts: Configurable alerts with multiple condition types
- Multi-channel Notifications: Telegram messages, phone calls with text-to-speech, console, and extensible notification system
- Account Management: View balances, positions, and account summary
- Trading Information: Access to instruments, order books, and market data
- MCP Integration: Full compatibility with Claude Desktop and other MCP clients
Installation
Prerequisites
- Python 3.10 or higher
- Deribit API credentials (for account operations)
- Telegram Bot Token (for notifications)
Setup
- Clone or navigate to the repository:
cd /path/to/mcp-server
- Create a virtual environment:
python3 -m venv venv
source venv/bin/activate # On macOS/Linux
# or
venv\Scripts\activate # On Windows
- Install dependencies:
pip3 install -e .
-
Configure Deribit API (optional, for account features):
- Go to https://www.deribit.com/account/api
- Create API credentials with appropriate permissions
- Note: You'll add these to your Claude Desktop config later
-
Configure Telegram Bot (for notifications):
a. Create a bot:
- Message @BotFather on Telegram
- Send
/newbotand follow the prompts - Save the bot token (e.g.,
123456789:ABCdefGHIjklMNOpqrsTUVwxyz)
b. Get your Chat ID:
- Message @userinfobot on Telegram
- It will reply with your user info including your chat ID
- Or send a message to your bot, then visit:
https://api.telegram.org/bot<YOUR_BOT_TOKEN>/getUpdates - Look for
"chat":{"id":123456789}in the response
c. Save credentials:
- You'll add these to your Claude Desktop config in the next step
-
Configure CallMeBot (optional, for phone call alerts):
a. Authorize CallMeBot (choose one method):
Method 1 - Web Authorization (Recommended):
- Visit: https://api2.callmebot.com/txt/auth.php
- Log in with your Telegram account
- Click "Authorize" to grant permissions
- You'll see a success page with a test URL
Method 2 - Telegram Bot:
- Message @CallMeBot_API on Telegram (note: use @CallMeBot_API, not @CallMeBot_txtbot)
- Send
/startto authorize your account - Wait for confirmation message
b. Get your Telegram username:
- Your username is in the format
@yourname(visible in Telegram Settings → Edit Profile) - Make sure to use the EXACT username shown in your Telegram profile
- Alternatively, you can use your phone number in international format (e.g.,
+1234567890)
c. Add to config:
- Add
CALLMEBOT_USERNAMEto your Claude Desktop config (see next section) - Use the exact username from your Telegram profile (case-sensitive)
- You can also customize the voice language with
CALLMEBOT_DEFAULT_LANG(default:en-US-Standard-B)
Configuration
For Local Testing (Optional)
If you want to run the server directly (not through Claude Desktop), create a .env file:
cp .env.example .env
Edit .env with your settings:
# Deribit API (optional - for account features)
DERIBIT_API_KEY=your_api_key_here
DERIBIT_API_SECRET=your_api_secret_here
DERIBIT_TEST_MODE=true # Set to false for production
# Telegram Notifications
TELEGRAM_BOT_TOKEN=your_telegram_bot_token_here
TELEGRAM_CHAT_ID=your_telegram_chat_id_here
# CallMeBot (Optional - for phone call alerts with TTS)
CALLMEBOT_USERNAME=@yourname # Or phone number like +1234567890
CALLMEBOT_DEFAULT_LANG=en-US-Standard-B # TTS voice/language
CALLMEBOT_REPEAT_COUNT=1 # Number of times to repeat the message
# Logging
LOG_LEVEL=INFO
Note: The .env file is only used for local development/testing. For Claude Desktop integration, you must include these values in the claude_desktop_config.json file (see next section).
Usage
Running the Server
Direct execution:
python -m src.server
With uv:
uv run python -m src.server
Claude Desktop Integration
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Important: When using Claude Desktop, you must include ALL environment variables (including Telegram credentials) in the env section, as the .env file is not automatically loaded.
{
"mcpServers": {
"deribit": {
"command": "/absolute/path/to/mcp-server/venv/bin/python",
"args": ["-m", "src.server"],
"cwd": "/absolute/path/to/mcp-server",
"env": {
"DERIBIT_TEST_MODE": "true",
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"TELEGRAM_BOT_TOKEN": "your_telegram_bot_token_here",
"TELEGRAM_CHAT_ID": "your_telegram_chat_id_here",
"CALLMEBOT_USERNAME": "@yourname"
}
}
}
}
Note:
- Use the full path to your virtual environment's Python executable
- Include Telegram credentials directly in the config for notifications to work
- Set
DERIBIT_TEST_MODEtofalsefor production trading - Optionally add
DERIBIT_API_KEYandDERIBIT_API_SECRETto theenvsection for account features
Available Tools
set_price_alert
Create a price alert for an instrument.
Parameters:
instrument: Trading instrument (e.g., "BTC-PERPETUAL")condition: Alert type - "above", "below", "crosses_above", "crosses_below", "percentage_change"threshold: Price level or percentagenotification_channel: "telegram" (text message), "telegram_call" (phone call with TTS), or "console"message: Custom alert message (optional)repeat: Re-trigger after cooldown (default: false)
Examples:
Set a price alert for BTC-PERPETUAL above $100,000 via Telegram
Set a phone call alert for ETH-PERPETUAL below $3,000
remove_alert
Remove an existing alert.
Parameters:
alert_id: Alert ID to remove
list_alerts
List all configured alerts with optional filtering.
Parameters:
instrument: Filter by instrument (optional)status: Filter by status (optional)
get_current_price
Get the current price for an instrument.
Parameters:
instrument: Trading instrument
get_instruments
List available trading instruments.
Parameters:
currency: Currency code (default: "BTC")kind: "future", "option", or "spot"
get_account_summary
View account balance and equity.
Parameters:
currency: Currency code (default: "BTC")
get_positions
List all open positions.
Parameters:
currency: Currency code (default: "BTC")
Resources
deribit://price/{instrument}
Real-time price data for an instrument.
deribit://alerts
JSON list of all configured alerts.
deribit://account/{currency}
Account summary information.
Alert Conditions
- above: Triggers when price goes above threshold
- below: Triggers when price goes below threshold
- crosses_above: Triggers when price crosses up through threshold
- crosses_below: Triggers when price crosses down through threshold
- percentage_change: Triggers on percentage change from last check
Example Use Cases
Basic Price Monitoring
"Set an alert for BTC-PERPETUAL when it goes above $100,000"
Phone Call Alert
"Call me when BTC-PERPETUAL crosses above $105,000"
"Set a phone call alert for ETH-PERPETUAL below $3,000"
Crossing Alert
"Alert me when ETH-PERPETUAL crosses below $3,500"
Percentage Change
"Set a 5% change alert for BTC-PERPETUAL"
Check Current Price
"What's the current price of BTC-PERPETUAL?"
View Alerts
"Show me all my active alerts"
Account Management
"What's my BTC account balance?"
"Show my open positions"
Development
Project Structure
mcp-server/
├── src/ # Telegram implementation
│ ├── __init__.py
│ ├── server.py # Main MCP server (Telegram)
│ ├── config.py # Configuration management
│ ├── deribit_ws.py # WebSocket client
│ ├── deribit_rest.py # REST API client
│ ├── alerts.py # Alert management
│ └── notifications.py # Notification system (Telegram)
├── src-signal/ # Signal Messenger implementation
│ ├── __init__.py
│ ├── server.py # Main MCP server (Signal)
│ ├── config.py # Configuration management (Signal)
│ ├── deribit_ws.py # WebSocket client (shared)
│ ├── deribit_rest.py # REST API client (shared)
│ ├── alerts.py # Alert management (shared)
│ └── notifications.py # Notification system (Signal)
├── pyproject.toml # Project dependencies
├── .env.example # Example environment config
├── README.md # Telegram documentation
└── README-signal.md # Signal documentation
Running Tests
pytest tests/
Code Formatting
black src/
ruff check src/
Security Considerations
- API Credentials: Never commit
.envfile to version control - Test Mode: Use
DERIBIT_TEST_MODE=truefor testing - Permissions: Limit Deribit API permissions to minimum required
- Notifications: Secure your Telegram bot token
Troubleshooting
Connection Issues
If WebSocket connection fails:
- Check internet connectivity
- Verify Deribit API status
- Try test environment first (
DERIBIT_TEST_MODE=true)
Authentication Errors
If API authentication fails:
- Verify API key and secret
- Check API key permissions on Deribit
- Ensure credentials are in
.envfile
Telegram Notifications
If notifications don't arrive:
-
Check environment variables in Claude Desktop config:
- Most common issue: Telegram credentials not in
claude_desktop_config.json - The
.envfile is NOT read by Claude Desktop - You MUST add
TELEGRAM_BOT_TOKENandTELEGRAM_CHAT_IDto theenvsection of your config
- Most common issue: Telegram credentials not in
-
Verify credentials:
- Check bot token is correct
- Check chat ID is correct (should be a number like
1950437710) - Send a message to your bot first (so it knows your chat ID)
-
Check logs (macOS):
tail -f ~/Library/Logs/Claude/mcp-server-deribit.log- Look for "Initialized Telegram notification channel" (good)
- Or "Telegram credentials not found" (means env vars not set correctly)
-
Test notification on startup:
- When the server starts, it sends a test message
- If you receive this, Telegram is configured correctly
- If not, check your Claude Desktop config
CallMeBot Phone Calls
If phone call alerts don't work:
-
Verify authorization:
- Best method: Visit https://api2.callmebot.com/txt/auth.php and authorize with your Telegram account
- Or send
/startto @CallMeBot_API (not @CallMeBot_txtbot) - Check authorization status:
curl "http://api.callmebot.com/start.php?user=@yourname&text=test"
-
Check username format:
- Use EXACT format
@yournamefrom Telegram Settings → Edit Profile - Username is case-sensitive and must match exactly
- Or use international phone format like
+1234567890 - Common mistake: using wrong username (verify in Telegram app)
- Use EXACT format
-
Check environment variable:
- Make sure
CALLMEBOT_USERNAMEis set correctly in Claude Desktop config - Must match the username you authorized with CallMeBot
- Restart Claude Desktop after changes
- Make sure
-
Check logs (macOS):
tail -f ~/Library/Logs/Claude/mcp-server-deribit.log- Look for "Telegram call channel initialized for @yourname" (good)
- Look for "Successfully initiated call to @yourname" (call was sent)
- Or "CallMeBot username not configured" (means env var not set)
- Or "HTTP Request: GET http://api.callmebot.com/start.php" (shows API call)
-
Test with a simple alert:
- Try: "Set a telegram_call alert for BTC-PERPETUAL above $1"
- This should trigger immediately if price is above $1
- Check logs to see if "Successfully initiated call" appears
Note: There's a known issue with audio playback on iOS Telegram app. Android and Desktop work better.
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
MIT License - see LICENSE file for details
Support
For issues and questions:
- Check the MCP documentation
- Review Deribit API docs
- Open an issue on GitHub
Acknowledgments
- Built with FastMCP
- Integrates with Deribit Exchange
- Notifications via python-telegram-bot
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。