Back to Details

robonet-workbench

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Robonet MCP Integration

Robonet MCP 集成

Overview

概述

Robonet provides an MCP server that enables AI assistants to build, test, and deploy trading strategies. The server offers 24 tools organized into 6 categories: Data Access (8), AI-Powered Strategy Generation (6), Backtesting (2), Prediction Markets (3), Deployment (4), and Account Management (2).
Robonet提供一款MCP服务器，支持AI助手构建、测试和部署交易策略。该服务器提供24种工具，分为6大类：数据访问（8种）、AI驱动策略生成（6种）、回测（2种）、预测市场（3种）、部署（4种）和账户管理（2种）。

Quick Start

快速开始

Load the required MCP tools before using them:
Use MCPSearch to select: mcp__workbench__get_all_symbols
Use MCPSearch to select: mcp__workbench__create_strategy
Use MCPSearch to select: mcp__workbench__run_backtest
After loading, call the tools directly to interact with Robonet.
在使用前加载所需的MCP工具：
Use MCPSearch to select: mcp__workbench__get_all_symbols
Use MCPSearch to select: mcp__workbench__create_strategy
Use MCPSearch to select: mcp__workbench__run_backtest
加载完成后，可直接调用这些工具与Robonet交互。

Tool Categories

工具分类

1. Data Access Tools (Fast, <1s execution)

1. 数据访问工具（执行速度快，<1秒）

Browse available resources before building strategies:
  • get_all_strategies
     - List your trading strategies with optional backtest results
  • get_strategy_code
     - View Python source code of a strategy
  • get_strategy_versions
     - Track strategy evolution across versions
  • get_all_symbols
     - List tradeable pairs on Hyperliquid (BTC-USDT, ETH-USDT, etc.)
  • get_all_technical_indicators
     - Browse 170+ indicators (RSI, MACD, Bollinger Bands, etc.)
  • get_allora_topics
     - List Allora Network ML prediction topics
  • get_data_availability
     - Check data ranges before backtesting
  • get_latest_backtest_results
     - View recent backtest performance
Pricing: Most $0.001, some free. Use these liberally to explore.
When to use: Start every workflow by checking available symbols, indicators, or existing strategies before generating new code.
在构建策略前浏览可用资源：
  • get_all_strategies
     - 列出你的交易策略，可选择包含回测结果
  • get_strategy_code
     - 查看策略的Python源代码
  • get_strategy_versions
     - 跟踪策略的版本迭代
  • get_all_symbols
     - 列出Hyperliquid上的可交易对（如BTC-USDT、ETH-USDT等）
  • get_all_technical_indicators
     - 浏览170+种技术指标（如RSI、MACD、布林带等）
  • get_allora_topics
     - 列出Allora Network的ML预测主题
  • get_data_availability
     - 回测前检查数据覆盖范围
  • get_latest_backtest_results
     - 查看近期回测表现
定价：大部分为0.001美元，部分免费。可随意使用这些工具进行探索。
适用场景：在生成新代码前，先通过这些工具查看可用交易对、指标或现有策略，开启每个工作流。

2. AI-Powered Strategy Tools (20-60s execution)

2. AI驱动策略工具（执行时间20-60秒）

Generate and improve trading strategies:
  • generate_ideas
     - Get AI-generated strategy concepts based on market data
  • create_strategy
     - Generate complete Python strategy from description
  • optimize_strategy
     - Tune parameters for better performance
  • enhance_with_allora
     - Add Allora Network ML predictions to strategy
  • refine_strategy
     - Make targeted code improvements
  • create_prediction_market_strategy
     - Generate Polymarket YES/NO trading logic
Pricing: Real LLM cost + margin ($0.50-$4.50 typical). These are the most expensive tools.
When to use: After understanding available resources, use these to build or improve strategies. Always backtest after generation.
生成和优化交易策略：
  • generate_ideas
     - 根据市场数据获取AI生成的策略概念
  • create_strategy
     - 根据描述生成完整的Python策略代码
  • optimize_strategy
     - 调整参数以提升策略表现
  • enhance_with_allora
     - 为策略添加Allora Network的ML预测
  • refine_strategy
     - 针对性优化代码
  • create_prediction_market_strategy
     - 生成Polymarket的YES/NO交易逻辑
定价：实际LLM成本+边际费用（通常0.50-4.50美元）。这些是成本最高的工具。
适用场景：了解可用资源后，使用这些工具构建或优化策略。生成策略后务必进行回测。

3. Backtesting Tools (20-40s execution)

3. 回测工具（执行时间20-40秒）

Test strategy performance on historical data:
  • run_backtest
     - Test crypto trading strategies
  • run_prediction_market_backtest
     - Test Polymarket strategies
Pricing: $0.001 per backtest
Returns: Performance metrics (Sharpe ratio, max drawdown, win rate, total return, profit factor), trade statistics, equity curve data
When to use: After creating or modifying a strategy, always backtest before deploying. Use multiple time periods to validate robustness.
在历史数据上测试策略表现：
  • run_backtest
     - 测试加密货币交易策略
  • run_prediction_market_backtest
     - 测试Polymarket策略
定价：每次回测0.001美元
返回结果：表现指标（夏普比率、最大回撤、胜率、总收益率、盈利因子）、交易统计数据、权益曲线数据
适用场景：创建或修改策略后，部署前务必进行回测。使用多个时间段验证策略的稳健性。

4. Prediction Market Tools

4. 预测市场工具

Build Polymarket trading strategies:
  • get_all_prediction_events
     - Browse available prediction markets
  • get_prediction_market_data
     - Analyze YES/NO token price history
  • create_prediction_market_strategy
     - Generate Polymarket strategy code
Pricing: $0.001 for data tools, Real LLM cost + margin for creation
When to use: For prediction market trading strategies on Polymarket (politics, crypto price predictions, economics events)
构建Polymarket交易策略：
  • get_all_prediction_events
     - 浏览可用的预测市场
  • get_prediction_market_data
     - 分析YES/NO代币的价格历史
  • create_prediction_market_strategy
     - 生成Polymarket策略代码
定价：数据工具为0.001美元，策略生成工具为实际LLM成本+边际费用
适用场景：用于Polymarket上的预测市场交易策略（政治、加密货币价格预测、经济事件等）

5. Deployment Tools

5. 部署工具

Deploy strategies to live trading on Hyperliquid:
  • deployment_create
     - Launch live trading agent (EOA or Hyperliquid Vault)
  • deployment_list
     - Monitor active deployments
  • deployment_start
     - Resume stopped deployment
  • deployment_stop
     - Halt live trading
Pricing: $0.50 to create, free for list/start/stop
Constraints:
  • EOA (wallet): Max 1 active deployment per wallet
  • Hyperliquid Vault: Requires 200+ USDC in wallet, unlimited deployments
When to use: After thorough backtesting shows positive results. Never deploy without backtesting first.
将策略部署到Hyperliquid进行实盘交易：
  • deployment_create
     - 启动实盘交易代理（EOA或Hyperliquid Vault）
  • deployment_list
     - 监控活跃的部署任务
  • deployment_start
     - 恢复已停止的部署任务
  • deployment_stop
     - 暂停实盘交易
定价：创建部署需0.50美元，列表/启动/停止操作免费
限制条件：
  • EOA（外部账户钱包）：每个钱包最多1个活跃部署任务
  • Hyperliquid Vault：钱包中需有200+ USDC，支持无限部署任务
适用场景：经过充分回测确认策略表现良好后再部署。绝不跳过回测直接部署。

6. Account Tools

6. 账户工具

Manage credits and view account info:
  • get_credit_balance
     - Check available USDC credits
  • get_credit_transactions
     - View transaction history
Pricing: Free
When to use: Check balance before expensive operations. Monitor spending via transaction history.
管理信用额度并查看账户信息：
  • get_credit_balance
     - 查看可用USDC信用额度
  • get_credit_transactions
     - 查看交易历史
定价：免费
适用场景：在进行高成本操作前检查余额。通过交易历史监控支出情况。

Common Workflows

常见工作流

Workflow 1: Create and Test New Strategy

工作流1：创建并测试新策略

1. get_all_symbols → See available trading pairs
2. get_all_technical_indicators → Browse indicators
3. create_strategy → Generate Python code from description
4. run_backtest → Test on 6+ months of data
5. If promising: optimize_strategy → Tune parameters
6. If excellent: enhance_with_allora → Add ML signals
7. run_backtest → Validate improvements
8. If ready: deployment_create → Deploy to live trading
Cost: ~$1-5 depending on optimization and enhancement
1. get_all_symbols → 查看可用交易对
2. get_all_technical_indicators → 浏览技术指标
3. create_strategy → 根据描述生成Python代码
4. run_backtest → 使用6个月以上的数据进行测试
5. 若表现良好：optimize_strategy → 调整参数
6. 若表现优秀：enhance_with_allora → 添加ML信号
7. run_backtest → 验证优化效果
8. 若准备就绪：deployment_create → 部署到实盘交易
成本：约1-5美元，取决于优化和增强操作

Workflow 2: Enhance Existing Strategy

工作流2：优化现有策略

1. get_all_strategies (include_latest_backtest=true) → Find strategy
2. get_strategy_code → Review implementation
3. refine_strategy (mode="new") → Make targeted improvements
4. run_backtest → Test changes
5. If better: enhance_with_allora → Add ML predictions
6. run_backtest → Final validation
Cost: ~$0.50-2.00
1. get_all_strategies (include_latest_backtest=true) → 查找目标策略
2. get_strategy_code → 查看实现代码
3. refine_strategy (mode="new") → 针对性优化
4. run_backtest → 测试修改效果
5. 若表现提升：enhance_with_allora → 添加ML预测
6. run_backtest → 最终验证
成本：约0.50-2.00美元

Workflow 3: Prediction Market Trading

工作流3：预测市场交易

1. get_all_prediction_events → Browse markets
2. get_prediction_market_data → Analyze price history
3. create_prediction_market_strategy → Build YES/NO logic
4. run_prediction_market_backtest → Test performance
5. If profitable: deployment_create → Deploy (when supported)
Cost: ~$0.50-5.00
1. get_all_prediction_events → 浏览预测市场
2. get_prediction_market_data → 分析价格历史
3. create_prediction_market_strategy → 构建YES/NO交易逻辑
4. run_prediction_market_backtest → 测试策略表现
5. 若盈利：deployment_create → 部署（支持时）
成本：约0.50-5.00美元

Workflow 4: Explore Ideas Before Building

工作流4：构建前探索思路

1. get_all_symbols → Check available pairs
2. get_allora_topics → See ML prediction coverage
3. generate_ideas (strategy_count=3) → Get AI concepts
4. Pick favorite idea
5. create_strategy → Implement chosen concept
6. run_backtest → Validate
Cost: ~$0.50-4.50 (use generate_ideas to explore cheaply)
1. get_all_symbols → 查看可用交易对
2. get_allora_topics → 查看ML预测覆盖范围
3. generate_ideas (strategy_count=3) → 获取AI生成的策略概念
4. 选择心仪的思路
5. create_strategy → 实现选定的策略
6. run_backtest → 验证效果
成本：约0.50-4.50美元（使用generate_ideas可低成本探索）

Strategy Development Best Practices

策略开发最佳实践

Start with Data Exploration

从数据探索开始

Always check availability before building:
  • Use 
    get_data_availability
    to verify symbol has sufficient history
  • Check 
    get_allora_topics
    if planning ML enhancement
  • Review 
    get_all_technical_indicators
    to know what's available
构建策略前务必确认数据可用性：
  • 使用
    get_data_availability
    验证交易对是否有足够的历史数据
  • 若计划使用ML增强，查看
    get_allora_topics
  • 查看
    get_all_technical_indicators
    了解可用指标

Always Backtest

务必进行回测

Never deploy without backtesting:
  • Test on 6+ months of data minimum
  • Use multiple time periods (train vs validation)
  • Check metrics: Sharpe >1.0, max drawdown <20%, win rate 45-65%
  • Compare performance across different market conditions
绝不跳过回测直接部署：
  • 至少使用6个月以上的数据进行测试
  • 使用多个时间段（训练集 vs 验证集）
  • 检查指标：夏普比率>1.0，最大回撤<20%，胜率45-65%
  • 比较策略在不同市场环境下的表现

Cost Management

成本管理

Tools are priced in tiers:
  1. Data tools ($0.001 or free) - Use liberally
  2. Backtesting ($0.001) - Use frequently
  3. AI generation (LLM cost + margin) - Most expensive
  4. Deployment ($0.50) - One-time per deployment
Cost-saving tips:
  • Use 
    generate_ideas
    ($0.05-0.50) before 
    create_strategy
    ($1-4)
  • Check 
    get_latest_backtest_results
    (free) before running new backtest
  • Use 
    refine_strategy
    ($0.50-1.50) instead of regenerating with 
    create_strategy
  • Review 
    get_strategy_code
    (free) before modifying
工具分为不同定价层级：
  1. 数据工具（0.001美元或免费）- 可随意使用
  2. 回测工具（0.001美元）- 可频繁使用
  3. AI生成工具（LLM成本+边际费用）- 成本最高
  4. 部署工具（0.50美元）- 每次部署一次性收费
成本节约技巧：
  • 在使用
    create_strategy
    （1-4美元）前，先使用
    generate_ideas
    （0.05-0.50美元）
  • 运行新回测前，先查看
    get_latest_backtest_results
    （免费）
  • 使用
    refine_strategy
    （0.50-1.50美元）替代
    create_strategy
    重新生成代码
  • 修改前查看
    get_strategy_code
    （免费）

Strategy Naming Convention

策略命名规范

Follow this pattern: 
{Name}_{RiskLevel}[_suffix]
Examples:
  • RSIMeanReversion_M
    - Base strategy, medium risk
  • MomentumBreakout_H_optimized
    - After optimization, high risk
  • TrendFollower_L_allora
    - With Allora ML, low risk
Risk levels: H (high), M (medium), L (low)
遵循以下格式：
{名称}_{风险等级}[_后缀]
示例：
  • RSIMeanReversion_M
    - 基础策略，中等风险
  • MomentumBreakout_H_optimized
    - 优化后策略，高风险
  • TrendFollower_L_allora
    - 集成Allora ML预测，低风险
风险等级：H（高）、M（中）、L（低）

Technical Details

技术细节

Strategy Framework

策略框架

Strategies use the Jesse trading framework with these required methods:
  • should_long()
    - Check if conditions met for long entry
  • should_short()
    - Check if conditions met for short entry
  • go_long()
    - Execute long entry with position sizing
  • go_short()
    - Execute short entry with position sizing
Optional methods:
  • on_open_position(order)
    - Set stop loss, take profit after entry
  • update_position()
    - Trailing stops, position management
  • should_cancel_entry()
    - Cancel unfilled orders
策略基于Jesse交易框架开发，需包含以下必填方法：
  • should_long()
    - 检查是否满足做多入场条件
  • should_short()
    - 检查是否满足做空入场条件
  • go_long()
    - 执行做多入场并设置仓位大小
  • go_short()
    - 执行做空入场并设置仓位大小
可选方法：
  • on_open_position(order)
    - 入场后设置止损、止盈
  • update_position()
    - 跟踪止损、仓位管理
  • should_cancel_entry()
    - 取消未成交订单

Available Indicators

可用指标

170+ technical indicators via 
jesse.indicators
:
  • Momentum: RSI, MACD, Stochastic, ADX, CCI, MFI
  • Trend: EMA, SMA, Supertrend, Parabolic SAR, VWAP
  • Volatility: Bollinger Bands, ATR, Keltner Channels
  • Volume: OBV, Volume Profile, Chaikin Money Flow
  • And many more...
Use 
get_all_technical_indicators
to see the full list.
通过
jesse.indicators
提供170+种技术指标：
  • 动量指标：RSI、MACD、随机指标、ADX、CCI、MFI
  • 趋势指标：EMA、SMA、Supertrend、抛物转向指标、VWAP
  • 波动率指标：布林带、ATR、肯特纳通道
  • 成交量指标：OBV、成交量分布、蔡金资金流
  • 以及更多...
使用
get_all_technical_indicators
查看完整列表。

Allora Network Integration

Allora Network集成

Add ML price predictions to strategies:
  • Prediction types: Log return (percentage change) or absolute price
  • Horizons: 5m, 8h, 24h, 1 week
  • Assets: BTC, ETH, SOL, NEAR
  • Networks: Mainnet (10 topics) and Testnet (26 topics)
Use 
enhance_with_allora
to automatically integrate predictions, or manually add via 
self.get_predictions()
in strategy code.
为策略添加ML价格预测：
  • 预测类型：对数收益率（百分比变化）或绝对价格
  • 预测周期：5分钟、8小时、24小时、1周
  • 支持资产：BTC、ETH、SOL、NEAR
  • 网络：主网（10个主题）和测试网（26个主题）
使用
enhance_with_allora
自动集成预测，或在策略代码中通过
self.get_predictions()
手动添加。

Deployment Options

部署选项

EOA (Externally Owned Account):
  • Direct wallet trading
  • Max 1 active deployment per wallet
  • Immediate deployment
  • Lower setup complexity
Hyperliquid Vault:
  • Requires 200+ USDC in wallet
  • Unlimited deployments
  • Professional vault setup
  • Public TVL and performance tracking
EOA（外部账户钱包）：
  • 直接通过钱包交易
  • 每个钱包最多1个活跃部署任务
  • 部署即时生效
  • 设置复杂度低
Hyperliquid Vault：
  • 钱包中需有200+ USDC
  • 支持无限部署任务
  • 专业级金库设置
  • 公开TVL和表现跟踪

Troubleshooting

故障排除

"Insufficient Credits" Error

"信用额度不足"错误

Check balance: 
get_credit_balance
Purchase credits in Robonet dashboard if needed
查看余额：
get_credit_balance
若需要，在Robonet控制台购买信用额度

"No Data Available" for Backtest

回测时显示"无可用数据"

Use 
get_data_availability
to check symbol coverage Try shorter date range or different symbol BTC-USDT and ETH-USDT have longest history (2020-present)
使用
get_data_availability
检查交易对的数据覆盖范围 尝试缩短时间范围或更换交易对 BTC-USDT和ETH-USDT的历史数据最久（2020年至今）

"No Trades Generated" in Backtest

回测时"未生成交易"

Entry conditions may be too restrictive Try longer test period or adjust thresholds Use 
get_strategy_code
to review logic
入场条件可能过于严格 尝试延长测试时间或调整阈值 使用
get_strategy_code
查看策略逻辑

Backtest Takes >2 Minutes

回测耗时超过2分钟

Long date ranges (>2 years) or high-frequency timeframes (1m) are slow Use shorter ranges or lower frequency timeframes
长时间范围（>2年）或高频时间框架（1分钟）会导致速度缓慢 使用更短的时间范围或更低频率的时间框架

Strategy Not Showing in Web Interface

策略未在Web界面显示

Strategies are linked to API key's wallet Ensure logged into same account that owns the API key Refresh "My Strategies" page
策略与API密钥绑定的钱包关联 确保登录的账户与API密钥所属账户一致 刷新"我的策略"页面

Complete Tool Reference

完整工具参考

For detailed parameter documentation on all 24 tools, see:
  • ../../shared-references/tool-catalog.md
The catalog includes:
  • Full parameter specifications with types and defaults
  • Return value descriptions
  • Pricing for each tool
  • Execution time estimates
  • Usage examples
如需了解所有24种工具的详细参数文档，请查看：
  • ../../shared-references/tool-catalog.md
该文档包含：
  • 完整的参数说明（类型和默认值）
  • 返回值描述
  • 各工具定价
  • 执行时间预估
  • 使用示例

Example Prompts

示例提示词

Create a simple strategy:
Use Robonet MCP to create a momentum strategy for BTC-USDT on 4h timeframe that:
- Enters long when RSI crosses above 30 and price is above 50-day EMA
- Exits with 2% stop loss or 4% take profit
- Uses 95% of available margin
Backtest existing strategy:
Backtest my RSIMeanReversion_M strategy on ETH-USDT 1h timeframe from 2024-01-01 to 2024-06-30
Optimize parameters:
Optimize the RSI period and stop loss percentage for my MomentumBreakout_H strategy on BTC-USDT 4h from 2024-01-01 to 2024-12-31
Add ML predictions:
Enhance my TrendFollower_M strategy with Allora predictions for ETH-USDT 8h timeframe and compare performance
Deploy to live trading:
Deploy my RSIMeanReversion_M_allora strategy to Hyperliquid on BTC-USDT 4h with 2x leverage using EOA deployment
创建简单策略：
Use Robonet MCP to create a momentum strategy for BTC-USDT on 4h timeframe that:
- Enters long when RSI crosses above 30 and price is above 50-day EMA
- Exits with 2% stop loss or 4% take profit
- Uses 95% of available margin
回测现有策略：
Backtest my RSIMeanReversion_M strategy on ETH-USDT 1h timeframe from 2024-01-01 to 2024-06-30
优化参数：
Optimize the RSI period and stop loss percentage for my MomentumBreakout_H strategy on BTC-USDT 4h from 2024-01-01 to 2024-12-31
添加ML预测：
Enhance my TrendFollower_M strategy with Allora predictions for ETH-USDT 8h timeframe and compare performance
部署到实盘交易：
Deploy my RSIMeanReversion_M_allora strategy to Hyperliquid on BTC-USDT 4h with 2x leverage using EOA deployment

Security & Access

安全与访问

  • All tools require valid API key from Robonet
  • Strategies are wallet-scoped (only creator can access)
  • Credits reserved atomically before execution
  • API keys never committed to version control
  • Use environment variables or secure config for API keys
  • 所有工具均需有效的Robonet API密钥
  • 策略与钱包绑定（仅创建者可访问）
  • 执行前会自动预留信用额度
  • API密钥切勿提交到版本控制系统
  • 使用环境变量或安全配置存储API密钥

Resources

资源