Advertise
MCP.so
Sign In

AI看线 - A股技术分析与AI预测工具 MCP Server

@QuantML-Github

Repository

Basic information

Category

Finance & Commerce

Transports

stdio

Author

QuantML-Github

About AI看线 - A股技术分析与AI预测工具 MCP Server

Python-based stock analysis tool that combines traditional technical analysis with AI prediction capabilities. Providing comprehensive stock analysis and forecasting using K-line charts, technical indicators, financial data, and news data. With CMD/WEB/MCP supported.

AI看线 - A股技术分析与AI预测工具 MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "AI-Kline": {
      "command": "python",
      "args": [
        "main.py",
        "--stock_code",
        "000001",
        "--period",
        "1年",
        "--save_path",
        "./output"
      ]
    }
  }
}

AI看线 - A股技术分析与AI预测工具 MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is AI看线?

AI看线是一个基于Python的A股分析工具，结合传统技术分析和人工智能预测功能。它利用K线图、技术指标、财务数据和新闻数据对股票进行全面分析及预测，适用于投资者和量化研究爱好者。

How to use AI看线?

支持三种使用方式：命令行运行python main.py --stock_code 000001；启动Web服务python web_app.py后访问http://localhost:5000输入股票代码；或通过MCP Server（uv run mcp_server.py）在LLM客户端配置streamable-http端点http://localhost:8000/mcp交互分析。

Key features of AI看线

  • 使用AKShare获取A股历史交易、财务和新闻数据
  • 计算MA、MACD、KDJ、RSI、布林带等多种技术指标
  • 生成静态PNG和交互式HTML K线图及技术指标图表
  • 利用多模态AI（如通义千问视觉模型）分析历史数据并预测走势
  • 提供简洁美观的Web界面进行交互式分析
  • 支持MCP协议，通过LLM自然语言交互随时分析股票

Use cases of AI看线

  • 对A股指定股票进行历史K线和技术指标可视化分析
  • 结合财务数据和新闻信息，获取AI生成的未来走势预测报告
  • 通过Web界面快速输入股票代码和周期，查看专业级图表与分析
  • 在LLM对话中直接调用MCP Server，实时分析当前关注的股票

Frequently asked questions

1

AI看线需要什么运行环境？

Python 3.8+，安装`requirements.txt`中的依赖包，并创建`.env`文件配置API_KEY和BASE_URL（需使用多模态模型，如`qwen-vl-max`）。

2

AI看线的分析结果是否准确？

不，本工具仅供学习和研究使用，不构成任何投资建议。AI分析基于历史数据和当前信息，不能保证未来走势的准确性。

3

如何启动MCP Server？

在项目目录下执行`uv run mcp_server.py`，然后在支持MCP的客户端（如Cherry-Studio）中添加streamable-http服务器，URL为`http://localhost:8000/mcp`。

4

数据来源是什么？

数据通过AKShare库获取A股股票的历史量价数据、财务数据和新闻信息，数据准确性和可用性受网络和数据源限制。

5

使用AI分析时需要配置什么API密钥？

需要在`.env`文件中设置API_KEY、BASE_URL和MODEL_NAME，且模型必须为多模态模型（例如`qwen-vl-max`），用于分析生成的图表并输出预测文本。

Comments

More Finance & Commerce MCP servers

3Dsellers MCP Server

3Dsellers

The hosted eBay MCP server for ecommerce sellers. Manage eBay, Amazon, Walmart, Etsy, Shopify and TikTok Shop listings, products, inventory, orders and buyer messages from Claude, ChatGPT, Cursor or any AI assistant. 120

K

Korea & Asia Everyday Calculators (kWhmate)

kWhmate

Free, no-key calculators with sources: household electricity bills and LED savings for Korea (KEPCO), Taiwan (Taipower), the Philippines (Meralco, updated monthly) and Japan (TEPCO); Seoul/Busan taxi fares, tourist tax r

DeepLedger

Deepledger

Connect QuickBooks Online to Claude, ChatGPT, Grok, Copilot, Gemini, Cursor and other AI Agents

fAlpha

fAlpha.ai, Inc.

Read-only US equity research for AI agents: fAlpha's model signal for a stock with the drivers behind it, signal history and flips, news sentiment, analyst coverage, SEC filings, FRED macro and fundamentals. Every result

Priors

priors-agents

On-chain credit pool for ERC-8004 AI agents on Robinhood Chain: agents borrow USDG, repay it and earn a public credit score. Contracts, SDK, CLI, MCP server (@priors/mcp), x402 helpers (@priors/x402) and an agent skill.

4
Advertise