Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xyonium/futu-opend-mcp/futuapi)<a href="https://agentmods.dev/skills/xyonium/futu-opend-mcp/futuapi"><img src="https://agentmods.dev/badge/skills/xyonium/futu-opend-mcp/futuapi.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00521 | $0.40830 |
| Opus 5 | $0.00260 | $0.20415 |
| Sonnet 5 | $0.00104 | $0.08166 |
| Haiku 4.5 | $0.00052 | $0.04083 |
Grade B, and why
futuapi scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls /home/user/.claude/skills/futuapi/scripts/trade/get_accounts.py 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 2,448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是富途 OpenAPI 编程助手,帮助用户使用 Python SDK 获取行情数据、执行交易操作、订阅实时推送。
语言规则
根据用户输入的语言自动回复。用户使用英文提问则用英文回复,使用中文提问则用中文回复,其他语言同理。语言不明确时默认使用中文。技术术语(如代码、API 名称、参数名)保持原文不翻译。
⚠️ 安全警告:交易涉及真实资金。默认使用 模拟环境(TrdEnv.SIMULATE),除非用户明确要求使用正式环境。
前提条件
- OpenD 必须运行且版本 >= 10.4.6408,默认地址
127.0.0.1:11111(可通过环境变量配置) - Python SDK:
futu-api>= 10.4.6408 - 加密货币功能:需要
futu-api>= 10.5.6508(首次提供OpenCryptoTradeContext)。检测方法:
若报python -c "from futu import OpenCryptoTradeContext" 2>&1ImportError/cannot import name,运行升级:pip install --upgrade "futu-api>=10.5.6508"
环境检查(SDK 版本、版本戳、OpenD 连通性)已内置到脚本的
common.py中,首次运行自动完整检查,1 小时内后续脚本跳过。检查未通过时脚本会报错并提示运行/install-futu-opend。
SDK 导入
from futu import *
启动 OpenD
当用户说"启动 OpenD"、"打开 OpenD"、"运行 OpenD"时,先检测本地是否已安装 OpenD,再决定下一步操作。
检测是否已安装
Windows:
Get-ChildItem -Path "C:\Users\$env:USERNAME\Desktop","C:\Program Files","C:\Program Files (x86)","D:\" -Recurse -Filter "*OpenD-GUI*.exe" -ErrorAction SilentlyContinue | Select-Object -First 1 -ExpandProperty FullName
MacOS:
ls /Applications/*OpenD-GUI*.app 2>/dev/null || mdfind "kMDItemFSName == '*OpenD-GUI*'" 2>/dev/null | head -1
判断逻辑
- 已安装(找到可执行文件):直接启动,不需要运行安装流程
- Windows:
Start-Process "找到的exe路径" - MacOS:
open "/Applications/找到的.app"
- Windows:
- 未安装(未找到):提示用户当前未检测到 OpenD,调用
/install-opend进入安装流程
股票代码格式
- 港股:
HK.00700(腾讯)、HK.09988(阿里巴巴) - 美股:
US.AAPL(苹果)、US.TSLA(特斯拉) - A 股-沪:
SH.600519(贵州茅台) - A 股-深:
SZ.000001(平安银行) - 新加坡股:
SG.D05(星展集团)、SG.U11(大华银行) - 马股:
MY.1155(马来亚银行)、MY.1295(Public Bank) - 日股:
JP.7203(丰田汽车)、JP.9984(软银集团) - SG 期货:
SG.CNmain(A50 指数期货主连)、SG.NKmain(日经期货主连) - 加密货币-币种/指数:
CC.BTC、CC.ETH、CC.SOL - 加密货币-币对:
CC.BTCUSD、CC.ETHUSD、CC.BTCHKD(币对代码不带/)
日股(JP)支持范围
- ✅ 正股行情:快照 / K 线 / 买卖盘 / 逐笔 / 分时 / 实时报价 / 资金流 / 资金分布 / 订阅推送 / 板块 / 板块成份股 / IPO 列表 / 复权因子 / 市场状态 / F10 基本面(公司概况、财报、估值)
- ✅ V1 选股
get_stock_filter --market JP:支持价格 / 市值排序等基础筛选。注意:API 只返回筛选/排序涉及的字段,其他字段(如未指定排序时的 price、未指定价格筛选时的 market_val)会是 0 - ✅ V2 选股
get_stock_screen:JSON 配置{"filters": [{"type": "simple_field", "field": "MARKET", "values": ["JP"]}]},全 JP 市场覆盖约 3800 只正股;复杂因子(基本面 / 技术形态 / 资金流等)优先用 V2 - ❌ 衍生品:
- 涡轮筛选:窝轮市场仅支持 HK/SG/MY,日股窝轮不可筛
- 期权链 / 期权到期日:调用
get_option_chain/get_option_expiration_date会返回错误码-1,错误信息期权标的仅支持港美正股ETF以及港指美指 - 期权筛选:
get_option_screen --markets JP_STOCK/JP_INDEX接口可调,all_count有统计(JP_STOCK ≈ 24500,JP_INDEX ≈ 13500),但data始终为空——SDK / 服务端的半完工状态,无可用期权明细 - 日股交易通道
- ❌ 港股专属:经纪队列(
get_broker_queue)仅支持港股,日股调用会报错 - 代码格式:
JP.<数字股票编号>,如JP.6758(索尼)
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- docs/API_LIMITS.md 5.3 KB
- docs/API_REFERENCE.md 16 KB
- docs/FIELD_MAPPING.md 6.6 KB
- docs/FUTURES_TRADING.md 5.1 KB
- docs/TROUBLESHOOTING.md 5.7 KB
- LEGAL_Futu_api_cn.md 3.4 KB
- LEGAL_Futu_api_en.md 4.1 KB
- LEGAL_zh.md 3.3 KB
- scripts/check_env.py 2.0 KB runs code
- scripts/common.py 29 KB runs code
- scripts/quote/get_ark_active_transaction.py 5.2 KB runs code
- scripts/quote/get_ark_fund_holding.py 5.3 KB runs code
- scripts/quote/get_ark_stock_dynamic.py 1.8 KB runs code
- scripts/quote/get_broker_queue.py 2.2 KB runs code
- scripts/quote/get_capital_distribution.py 3.4 KB runs code
- scripts/quote/get_capital_flow.py 3.2 KB runs code
- scripts/quote/get_company_executive_background.py 3.3 KB runs code
- scripts/quote/get_company_executives.py 4.5 KB runs code
- scripts/quote/get_company_operational_efficiency.py 5.7 KB runs code
- scripts/quote/get_company_profile.py 4.3 KB runs code
- scripts/quote/get_corporate_actions_buybacks.py 9.7 KB runs code
- scripts/quote/get_corporate_actions_dividends.py 4.7 KB runs code
- scripts/quote/get_corporate_actions_stock_splits.py 8.0 KB runs code
- scripts/quote/get_daily_short_volume.py 9.2 KB runs code
- scripts/quote/get_dividend_calendar.py 3.0 KB runs code
- scripts/quote/get_dividend_rank.py 5.9 KB runs code
- scripts/quote/get_earnings_beat_rank.py 6.7 KB runs code
- scripts/quote/get_earnings_calendar.py 6.1 KB runs code
- scripts/quote/get_economic_calendar.py 4.9 KB runs code
- scripts/quote/get_fed_watch_dot_plot.py 1.4 KB runs code
- scripts/quote/get_fed_watch_target_rate.py 1.4 KB runs code
- scripts/quote/get_financials_earnings_price_history.py 9.1 KB runs code
- scripts/quote/get_financials_earnings_price_move.py 5.2 KB runs code
- scripts/quote/get_financials_revenue_breakdown.py 6.9 KB runs code
- scripts/quote/get_financials_statements.py 8.9 KB runs code
- scripts/quote/get_future_info.py 2.0 KB runs code
- scripts/quote/get_global_state.py 2.0 KB runs code
- scripts/quote/get_heat_map_data.py 4.4 KB runs code
- scripts/quote/get_high_dividend_soe_rank.py 5.1 KB runs code
- scripts/quote/get_history_kl_quota.py 2.1 KB runs code
- scripts/quote/get_hot_list.py 5.2 KB runs code
- scripts/quote/get_indicator_calc_result.py 8.3 KB runs code
- scripts/quote/get_indicator_list.py 5.5 KB runs code
- scripts/quote/get_industrial_chain_by_plate.py 1.7 KB runs code
- scripts/quote/get_industrial_chain_detail.py 1.5 KB runs code
- scripts/quote/get_industrial_chain_list.py 3.2 KB runs code
- scripts/quote/get_industrial_plate_info.py 1.5 KB runs code
- scripts/quote/get_industrial_plate_stock.py 4.7 KB runs code
- scripts/quote/get_insider_holder_list.py 6.8 KB runs code
- scripts/quote/get_insider_trade_list.py 7.8 KB runs code
- scripts/quote/get_institution_distribution.py 2.2 KB runs code
- scripts/quote/get_institution_holding_change.py 5.0 KB runs code
- scripts/quote/get_institution_holding_list.py 5.7 KB runs code
- scripts/quote/get_institution_list.py 4.3 KB runs code
- scripts/quote/get_institution_profile.py 1.9 KB runs code
- scripts/quote/get_ipo_list.py 2.3 KB runs code
- scripts/quote/get_kline.py 8.0 KB runs code
- scripts/quote/get_macro_indicator_history.py 2.2 KB runs code
- scripts/quote/get_macro_indicator_list.py 2.0 KB runs code
- scripts/quote/get_market_state.py 2.3 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 2,448 lines · 521 tokens per session scan B 72ceb716782e
futuapi is a skill published in the GitHub repository xyonium/futu-opend-mcp (9 stars, last pushed 1mo ago), licensed MIT. It adds 521 tokens to every session and 40,830 once invoked, about $0.0026 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.