SkillAgentSearch skills...

Akshare-MCP

基于Akshare金融数据API的MCP服务器,提供港股、美股、A股历史行情数据的工具接口。(还没开发完,目前就是这三个工具,主要是akshare的数据接口太不友好了,很多接口非常不适合开发成MCP)

Install / Use

claude mcp add guangxiangdebizi -- npx -y github:guangxiangdebizi/Akshare-MCP

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

67/100

Supported Platforms

Claude Code
Claude Desktop

Tags

Our assessment of Akshare-MCP

Akshare-MCP scores 67/100 on our quality scale, 898th of 953 AI & Machine Learning skills we index.

Its MCP Server is 4.0 KB long, well organised into 25 sections with 11 code examples: a solid amount of guidance for an agent.

It has 10 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
26/30
Structure
20/20
Description
12/15
Adoption
4/20
Freshness
5/15

Maintenance, license and trust

  • The repository was last updated about 16 months ago. Expect some instructions to reference tool versions or APIs that have since changed.
  • Our last check on 2026-10-22 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 73/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

Akshare-MCP compared with similar skills

All 4 of these similar skills score higher than Akshare-MCP; compare them before choosing.

SkillScoreStarsUpdatedFormat
Akshare-MCP (this skill)by guangxiangdebizi671016mo agoMCP Server
claude-memby thedotmack100113.8ktodayCLAUDE.md
Agent-Reachby Panniantong100109.5k1d agoCLAUDE.md
Understand-Anythingby Egonex-AI10091.0ktodayCLAUDE.md
headroomby headroomlabs-ai10079.0ktodayCLAUDE.md

Frequently asked questions

How do I install Akshare-MCP?
Run claude mcp add guangxiangdebizi -- npx -y github:guangxiangdebizi/Akshare-MCP. The install tabs above show the steps for each supported agent.
Which AI agents does Akshare-MCP work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is Akshare-MCP safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 73/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is Akshare-MCP still maintained?
The repository was last updated about 16 months ago. Expect some instructions to reference tool versions or APIs that have since changed.

AkShare MCP 服务器

基于 FastMCP 2.0 和 SSE 协议的 AkShare 金融数据 MCP 服务器。

功能特性

  • 🚀 基于 SSE 协议,零依赖、即开即用
  • 📊 集成 AkShare 金融数据接口
  • 📋 Markdown 表格格式输出,美观易读
  • 🔧 支持环境变量配置
  • 📝 完整的日志记录
  • 🛡️ 参数验证和错误处理

已实现的工具

stock_us_hist - 美股历史行情数据

获取美股历史行情数据,支持不同周期和复权方式。

参数:

  • symbol: 美股代码,例如 '106.TTE' 或 'AAPL'
  • period: 数据周期,选择 {'daily', 'weekly', 'monthly'},默认 'daily'
  • start_date: 开始日期,格式 YYYYMMDD,默认 '20210101'
  • end_date: 结束日期,格式 YYYYMMDD,默认 '20240214'
  • adjust: 复权类型,''=未复权, 'qfq'=前复权, 'hfq'=后复权,默认 ''

返回数据:

  • 日期、开盘、收盘、最高、最低价格(美元)
  • 成交量(股)、成交额(美元)
  • 振幅、涨跌幅、涨跌额、换手率

stock_hk_hist - 港股历史行情数据

获取港股历史行情数据,支持不同周期和复权方式。

参数:

  • symbol: 港股代码,例如 '00593' 或 '08367'
  • period: 数据周期,选择 {'daily', 'weekly', 'monthly'},默认 'daily'
  • start_date: 开始日期,格式 YYYYMMDD,默认 '19700101'
  • end_date: 结束日期,格式 YYYYMMDD,默认 '22220101'
  • adjust: 复权类型,''=未复权, 'qfq'=前复权, 'hfq'=后复权,默认 ''

返回数据:

  • 日期、开盘、收盘、最高、最低价格(港元)
  • 成交量(股)、成交额(港元)
  • 振幅、涨跌幅、涨跌额、换手率

stock_zh_a_hist - A股历史行情数据

获取沪深京A股历史行情数据,支持不同周期和复权方式。

参数:

  • symbol: A股代码,例如 '000001'(平安银行) 或 '603777'
  • period: 数据周期,选择 {'daily', 'weekly', 'monthly'},默认 'daily'
  • start_date: 开始日期,格式 YYYYMMDD,默认 '20210301'
  • end_date: 结束日期,格式 YYYYMMDD,默认 '20240528'
  • adjust: 复权类型,''=不复权, 'qfq'=前复权, 'hfq'=后复权,默认 ''

返回数据:

  • 日期、股票代码、开盘、收盘、最高、最低价格(人民币)
  • 成交量(手,1手=100股)、成交额(元)
  • 振幅、涨跌幅、涨跌额、换手率

复权说明:

  • 前复权:保持当前价格不变,调整历史价格,适合技术分析
  • 后复权:保证历史价格不变,调整当前价格,适合量化研究

输出格式示例

所有工具都返回格式化的 Markdown 表格,包含以下信息:

美股/港股输出格式

# 美股历史行情数据

**股票代码**: AAPL  
**数据周期**: daily  
**日期范围**: 20240101 ~ 20240214  
**复权方式**: 前复权  
**数据条数**: 32 条  
**货币单位**: 美元 (USD)

| 日期       | 开盘   | 收盘   | 最高   | 最低   | 成交量    | 成交额      | 振幅  | 涨跌幅 | 涨跌额 | 换手率 |
|------------|--------|--------|--------|--------|-----------|-------------|-------|--------|--------|--------|
| 2024-01-02 | 187.15 | 185.64 | 187.90 | 182.73 | 52230000  | 9687420000  | 2.76  | -2.94  | -5.61  | 0.84   |
| 2024-01-03 | 184.22 | 184.25 | 185.88 | 183.43 | 47317000  | 8732510000  | 1.32  | -0.75  | -1.39  | 0.76   |

*数据来源:东方财富网*

A股输出格式

# A股历史行情数据

**股票代码**: 000001  
**数据周期**: daily  
**日期范围**: 20240101 ~ 20240528  
**复权方式**: 前复权  
**数据条数**: 95 条  
**货币单位**: 人民币 (CNY)  
**成交量单位**: 手 (1手=100股)

| 日期       | 股票代码 | 开盘  | 收盘  | 最高  | 最低  | 成交量  | 成交额       | 振幅  | 涨跌幅 | 涨跌额 | 换手率 |
|------------|----------|-------|-------|-------|-------|---------|-------------|-------|--------|--------|--------|
| 2024-01-02 | 000001   | 11.88 | 11.78 | 11.96 | 11.72 | 1052468 | 1241250000  | 2.03  | -0.84  | -0.10  | 0.38   |
| 2024-01-03 | 000001   | 11.74 | 11.65 | 11.80 | 11.58 | 892456  | 1042180000  | 1.87  | -1.10  | -0.13  | 0.32   |

*数据来源:东方财富网*  
*注:成交量单位为手,成交额单位为元*

安装依赖

pip install -r requirements.txt

启动服务器

方法一:直接运行主文件

python akshare_mcp_server.py

方法二:使用启动脚本

python start_server.py

环境变量配置

可以通过环境变量自定义服务器配置:

export HOST=127.0.0.1
export PORT=8005
export TRANSPORT=sse

客户端连接配置

在您的 MCP 客户端中添加以下配置:

{
  "mcpServers": {
    "akshare-mcp": {
      "type": "sse",
      "url": "http://127.0.0.1:8005/sse",
      "timeout": 60,
      "description": "AkShare金融数据MCP服务器"
    }
  }
}

使用示例

启动服务器后,您可以通过 MCP 客户端调用各种工具:

美股数据示例

获取苹果公司(AAPL)近期股价数据:
- symbol: "AAPL"
- period: "daily"
- start_date: "20240101"
- end_date: "20240214"
- adjust: "qfq"

港股数据示例

获取腾讯控股(00700)港股数据:
- symbol: "00700"
- period: "daily"
- start_date: "20240101"
- end_date: "20240214"
- adjust: "qfq"

A股数据示例

获取平安银行(000001)A股数据:
- symbol: "000001"
- period: "daily"
- start_date: "20240101"
- end_date: "20240528"
- adjust: "qfq"

日志

服务器日志会保存在 logs/akshare_mcp.log 文件中,包含详细的操作记录和错误信息。

项目结构

Ptrader-MCP/
├── akshare_mcp_server.py    # 主服务器文件
├── start_server.py          # 启动脚本
├── config.json              # 客户端连接配置
├── requirements.txt         # 依赖文件
├── README.md               # 使用说明
└── logs/                   # 日志目录

注意事项

  1. 确保网络连接正常,AkShare 需要访问外部数据源
  2. 某些接口可能有访问频率限制,请适当控制调用频率
  3. 数据仅供参考,投资决策请谨慎

许可证

本项目基于 MIT 许可证开源。

Related Skills

View on GitHub
GitHub Stars10
CategoryAI
Updated1y ago
Forks3

Languages

Python

Trust signals

73/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

2 medium1 info