MetaTrader5行情数据MCP服务 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.2 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
基于MCP协议的MetaTrader5数据服务器,提供实时市场行情、K线数据和技术指标计算能力。面向量化交易者、金融数据分析师和自动化交易系统开发者,集成MT5平台数据源,支持程序化接入。
MetaTrader5行情数据MCP服务 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
基于MCP协议的MetaTrader5数据服务器,提供实时市场行情、K线数据和技术指标计算能力。面向量化交易者、金融数据分析师和自动化交易系统开发者,集成MT5平台数据源,支持程序化接入。
MetaTrader5行情数据MCP服务 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/emerzon/mt-data-mcp
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"metatrader5----mcp--": {
"command": "npx",
"args": ["-y", "mt-data-mcp"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 MetaTrader5行情数据MCP服务 执行以下任务... Claude: [自动调用 MetaTrader5行情数据MCP服务 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"metatrader5____mcp__": {
"command": "npx",
"args": ["-y", "mt-data-mcp"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
mtdata is a Windows-first research and automation toolkit for MetaTrader 5 (MT5). It turns a running MT5 terminal into repeatable CLI commands, MCP tools, and a local Web API for market data, forecasting, regime detection, signal processing, risk analysis, and reporting.
Use it to explore ideas, build repeatable research workflows, and integrate MT5 data with assistants or local applications. It is a toolkit, not a trading strategy or financial advice.
| Category | What It Does | Key Tools |
|----------|--------------|-----------|
| Data | Fetch candles, ticks, market depth, and ranked market scans from MT5 | data_fetch_candles, data_fetch_ticks, market_depth_fetch, market_ticker, symbols_top_markets |
| Forecasting | Predict price paths with classical, ML, or foundation models | forecast_generate, forecast_backtest_run |
| Volatility | Estimate future price movement magnitude | forecast_volatility_estimate |
| Regimes | Detect trending, ranging, or crisis market states | regime_detect |
| Barriers | Calculate TP/SL hit probabilities via simulation | forecast_barrier_prob, forecast_barrier_optimize |
| Patterns | Identify candlestick, chart, Elliott, and fractal patterns | patterns_detect |
| Indicators | Compute 100+ technical indicators | data_fetch_candles --indicators |
| Denoising | Smooth price data to reveal trends | --denoise option |
| Temporal | Discover session effects and seasonal patterns | temporal_analyze |
| Multi-asset | Explore cross-symbol correlation, cointegration, and lead/lag relationships | correlation_matrix, cointegration_test, causal_discover_signals |
| Scanning | Screen MT5 symbols by spread, price change, volume, RSI, and SMA | symbols_top_markets, market_scan |
| Strategy Backtesting | Backtest simple SMA/EMA/RSI trading rules on MT5 candles | strategy_backtest |
| Trading | Place orders, manage positions, review realized performance, and estimate tail risk | trade_place, trade_close, trade_journal_analyze, trade_var_cvar_calculate |
| Async Training | Run heavyweight forecast training in the background and reuse cached models | forecast_train, forecast_task_status, forecast_task_wait, forecast_models_list, forecast_models_delete |
| News | Unified, ranked news + economic calendar relevant to a symbol | news |
| Fundamentals | US equity data, screening, news, calendars | finviz_fundamentals, finviz_screen, finviz_calendar |
| Options | Options chains and QuantLib barrier pricing | options_chain, options_barrier_price |
Notes: - market_depth_fetch is enabled only when MTDATA_ENABLE_MARKET_DEPTH_FETCH=1 and your broker provides Level 2/DOM data. - Options-chain tools depend on Yahoo Finance endpoint availability. The pure QuantLib calculator options_barrier_price works independently of external options-chain data.
pip install -e .
pip install -r requirements.txt
Prerequisites: Windows + Python 3.14 + MetaTrader 5 installed and running (demo account recommended). For the full install on Windows, also install Visual Studio Build Tools 2022 with the Desktop development with C++ workload. ```bash
conda create -n mtdata python=3.14 -y conda activate mtdata
Create a .env file in the project root:
```ini
MT5_LOGIN=12345678
MT5_PASSWORD=your_password
MT5_SERVER=your_broker_server
MT5_SERVER_TZ=Europe/Athens # Or use MT5_TIME_OFFSET_MINUTES=120
MTDATA_TRADE_GUARDRAILS_ENABLED=1
MTDATA_TRADE_ALLOWED_SYMBOLS=EURUSD,BTCUSD,XAUUSD
MTDATA_TRADE_MAX_VOLUME_BY_SYMBOL=EURUSD:0.50,BTCUSD:0.03
MTDATA_TRADE_MAX_RISK_PCT_OF_EQUITY=1.5
```
mtdata reads dozens of environment variables covering MT5 connection, timezone, MCP/Web API server settings, news embeddings, Finviz tuning, GPU acceleration, and more. See Environment Variables Reference for the full list, including the trade-guardrail variables and a starter .env template.
.env reference (MT5, MCP, Web API, GPU, etc.)垂直领域的MCP创新应用,架构清晰。但维护力度不足、社区反馈有限,需观察长期更新状况才能确定稳定性。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
经综合评估,MetaTrader5行情数据MCP服务 在MCP工具赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | mt-data-mcp |
| 原始描述 | 开源MCP工具:A MCP server for MetaTrader5 that provides market data and technical indicators。⭐12 · Python |
| Topics | MetaTrader5行情数据技术指标量化交易MCP协议 |
| GitHub | https://github.com/emerzon/mt-data-mcp |
| License | MIT |
| 语言 | Python |
收录时间:2026-05-25 · 更新时间:2026-05-30 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端