tradex-hub — security grade SAFE, quality 59/100

Security audit verdict: SAFE · quality 59/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by wolfjkd · MCP Server · ★ 50

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is tradex-hub safe to install? View the security audit →

About tradex-hub

tradex-hub AI金融智能决策中台 AKShare 封装 · eltdx 通达信协议 · astocksignals 信号模块 · 量化计算引擎 · SmartRouter 全量路由 · 本地 MCP Server · 99 个工具 项目定位 为 AI Agent(WorkBuddy / Claude Code / Cursor)提供 A 股金融数据 + 量化计算 + 决策支持的 MCP 接口。 三层能力模型: L1 数据获取层(65个工具):通过 SmartRouter 统一获取数据(行情/财务/估值/行业/新闻/宏观/涨停板/龙虎榜等) L2 计算引擎层(8个工具):技术指标计算6个、绩效指标计算2个 L3 决策支持层(16个工具):交易信号生成3个、多因子分析2个、条件选股2个、系统诊断5个、综合分析3个、技术分析引擎1个 数据源架构(v3.3.0): datasources 数据源层:38 个数据类型,48 个数据源注册到 SmartRouter SmartRouter 全量覆盖:L1 工具通过 统一获取数据,自动健康评分/降级/故障隔离 独占源标记:集合竞价/逐笔/F10(eltdx 独有)、涨停归因(同花顺独有)、解禁日历(东财独有)等标记为 eltdx 1.2.0:行情类第一主源(郑州节点,TCP 3.5ms),独有集合竞价/逐笔/F10 新闻资讯数据源:东财个股新闻直连、财联社实时电报、巨潮公告直连、新浪财经直连、百度经济日历/交易提醒/热搜、期货新闻、东财人气榜、雪球热度、机构持仓、同花顺问财等 数据源看板:(端口 8765),可视化查看数据源健康/路由/工具分布;MCP 工具 可在 Agent 对话中查询 v3.3.0 更新:新增 9 个 akshare 新闻资讯数据源(百度/东财人气

a-stockai-agentchina-stocksdata-aggregationfinancefinancial-datamcppythonquantitative-financetrading

Quick Facts

Stars50
Forks17
LanguagePython
CategoryMCP Server
Quality Score58.7333919995158/100
Open Issues1
Last Updated2026-09-22
Created2026-06-01
Platformsmcp, python
Est. Tokens~16k

Compatible Skills

These tools work well together with tradex-hub for enhanced workflows:

  • hhxg-top-hhxg-python — semantic(0.40)+complementary+same_lang+similar_pop+shared_platform (64%)
  • alphaevo — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (60%)
  • OpenAshare — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (60%)
  • Tushare-Finance-Skill-for-Claude-Code — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)

tradex-hub alternative? Top 6 similar tools

Looking for a tradex-hub alternative? If you're comparing tradex-hub with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • ashare-lake by rootSunc · ⭐ 125

    ASL · 本地可日更的 A 股研究湖 · 42 数据集 · MCP 供数 AI agent · 零 token 零注册 | Local A-share research lake — history for human

  • ApocData-skill by ApocData · ⭐ 51

    ApocData · AI-native financial database for China A-share market. Drop-in Skill / MCP for Claude,ChatGPT, Qwen

  • dartlab by eddmpython · ⭐ 220

    Korean DART + SEC EDGAR filings as structured Python data for company analysis

  • utcp-mcp by universal-tool-calling-protocol · ⭐ 202

    All-in-one MCP server that can connect your AI agents to any native endpoint, powered by UTCP

  • yfinance-mcp by narumiruna · ⭐ 192
  • PolyMCP by poly-mcp · ⭐ 170

    Polymcp provides a simple and efficient way to interact with MCP servers using custom agents

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is tradex-hub?

tradex-hub is A股 AI 金融智能决策中台 · 129 个 MCP 工具 · eltdx 通达信协议 + akshare + 同花顺 + 东财 + 本地数据 · SmartRouter 多源降级路由 · 免费零鉴权. It is categorized as a MCP Server with 50 GitHub stars.

What programming language is tradex-hub written in?

tradex-hub is primarily written in Python. It covers topics such as a-stock, ai-agent, china-stocks.

How do I install or use tradex-hub?

You can find installation instructions and usage details in the tradex-hub GitHub repository at github.com/wolfjkd/tradex-hub. The project has 50 stars and 17 forks, indicating an active community.

What are the best alternatives to tradex-hub?

The top alternatives to tradex-hub on Agent Skills Hub include ashare-lake, ApocData-skill, dartlab. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools