Paradex MCP Server
A bridge between AI assistants and the Paradex perpetual futures trading platform for managing accounts, vaults, and orders. It enables users to retrieve real-time market data, monitor positions, and execute trading strategies through the Model Context Protocol.
README
MCP Paradex Server
<!-- mcp-name: io.github.tradeparadex/mcp-paradex-py -->
Model Context Protocol (MCP) server implementation for the Paradex trading platform.
<a href="https://glama.ai/mcp/servers/cq4bz5ljqj"> <img width="380" height="200" src="https://glama.ai/mcp/servers/cq4bz5ljqj/badge" alt="Paradex Server MCP server" /> </a>
Overview
This project provides a bridge between AI assistants (like Claude) and the Paradex perpetual futures trading platform. Using the MCP standard, AI assistants can:
- Retrieve market data from Paradex
- Manage trading accounts and vaults
- Place and manage orders
- Monitor positions and balance
Prerequisites
- Python 3.10+
Installation
Quick Start
Cursor IDE
Click to automatically configure this MCP server in Cursor:
Claude Code CLI
claude mcp add paradex uvx mcp-paradex
Smithery (Claude Desktop)
npx -y @smithery/cli install @tradeparadex/mcp-paradex-py --client claude
Standard Installation
PyPI
pip install mcp-paradex
uvx (Recommended)
uvx mcp-paradex
Development Setup
-
Clone the repository:
git clone https://github.com/tradeparadex/mcp-paradex-py.git cd mcp-paradex-py -
Install development dependencies:
uv sync --dev --all-extras -
Run locally:
uv run mcp-paradex
Configuration
Environment Variables
Set these environment variables for authentication:
PARADEX_ENVIRONMENT: Set toprod,testnet, ornightly(default:prod)PARADEX_ACCOUNT_PRIVATE_KEY: Your Paradex account private key
Using .env File
cp .env.template .env
# Edit .env with your credentials
Client Configuration
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"paradex": {
"command": "uvx",
"args": ["mcp-paradex"],
"env": {
"PARADEX_ENVIRONMENT": "testnet",
"PARADEX_ACCOUNT_PRIVATE_KEY": "your_private_key"
}
}
}
}
Docker (local / stdio)
# Build image
docker build . -t tradeparadex/mcp-paradex-py
# Run (public only)
docker run --rm -i tradeparadex/mcp-paradex-py
# Run with trading capabilities
docker run --rm -e PARADEX_ACCOUNT_PRIVATE_KEY=your_key -i tradeparadex/mcp-paradex-py
Docker (AWS Lambda / HTTP)
Use Dockerfile.aws for remote deployments via AWS Lambda with the
Lambda Web Adapter.
The adapter bridges Lambda invocations to the server's HTTP endpoint,
so no Lambda-specific code is needed.
# Build
docker build -f Dockerfile.aws -t tradeparadex/mcp-paradex-py-aws .
# Test locally (mirrors Lambda config)
docker run --rm -p 8080:8080 \
-e MCP_TRANSPORT=streamable-http \
-e MCP_STATELESS=true \
-e MCP_PORT=8080 \
-e PARADEX_ENVIRONMENT=prod \
tradeparadex/mcp-paradex-py-aws
The server will be available at http://localhost:8080/mcp.
Deploying to Lambda:
- Push the image to ECR
- Create a Lambda function from the container image
- Set the Lambda Function URL invoke mode to
RESPONSE_STREAM - Set environment variables on the Lambda function:
MCP_TRANSPORT=streamable-httpMCP_STATELESS=truePARADEX_ENVIRONMENT=prod(ortestnet)PARADEX_ACCOUNT_PRIVATE_KEY=your_key(optional, for trading)
Available Resources and Tools
Resources
System Resources
paradex://system/config- Get Paradex system configurationparadex://system/time- Get current system timeparadex://system/state- Get system operational state
Market Resources
paradex://markets- List of available marketsparadex://market/summary/{market_id}- Detailed market information
Vault Resources
paradex://vaults- List all vaultsparadex://vaults/config- Global vault configurationparadex://vaults/balance/{vault_id}- Vault balanceparadex://vaults/summary/{vault_id}- Comprehensive vault summaryparadex://vaults/transfers/{vault_id}- Deposit/withdrawal historyparadex://vaults/positions/{vault_id}- Current trading positionsparadex://vaults/account-summary/{vault_id}- Trading account information
Tools
System Tools
paradex_system_config- Get global system configurationparadex_system_state- Get current system state
Market Tools
paradex_markets- Get detailed market informationparadex_market_summaries- Get market summaries with metricsparadex_funding_data- Get historical funding rate dataparadex_orderbook- Get current orderbook with customizable depthparadex_klines- Get historical candlestick dataparadex_trades- Get recent tradesparadex_bbo- Get best bid and offer
Account Tools
paradex_account_summary- Get account summaryparadex_account_positions- Get current positionsparadex_account_fills- Get trade fillsparadex_account_funding_payments- Get funding paymentsparadex_account_transactions- Get transaction history
Order Tools
paradex_open_orders- Get all open ordersparadex_create_order- Create new orderparadex_cancel_orders- Cancel existing ordersparadex_order_status- Get order statusparadex_orders_history- Get historical orders
Vault Tools
paradex_vaults- Get detailed vault informationparadex_vaults_config- Get global vault configurationparadex_vault_balance- Get vault balanceparadex_vault_summary- Get comprehensive vault summaryparadex_vault_transfers- Get deposit/withdrawal historyparadex_vault_positions- Get current vault positionsparadex_vault_account_summary- Get vault trading account info
Trading Analysis Prompts
Market Analysis
market_overview- Comprehensive crypto market overviewmarket_analysis- Detailed technical and microstructure analysis
Position and Portfolio Management
position_management- Comprehensive position analysiscreate_optimal_order- Design optimal order parametershedging_strategy- Develop effective hedging strategiesportfolio_risk_assessment- Thorough portfolio risk analysisliquidation_protection- Identify and mitigate liquidation risks
Investment Strategies
vault_analysis- Comprehensive vault analysis for investment decisionsfunding_rate_opportunity- Identify funding rate arbitrage opportunitiestrading_consultation- Interactive trading advice and consultation
Documentation MCP
Enhanced results with Paradex documentation access:
"paradex-docs-mcp": {
"command": "uvx",
"args": [
"--from",
"mcpdoc",
"mcpdoc",
"--urls",
"Paradex:https://docs.paradex.trade/llms.txt",
"--transport",
"stdio"
]
}
Contributing
Please see CONTRIBUTING.md for information on how to contribute to this project, development setup, and our coding standards.
License
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。