Fenshitu MCP
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Fenshitu MCPgenerate intraday chart for 000001"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Fenshitu MCP
A-share stock intraday chart generation MCP (Model Context Protocol) service. Generates professional stock charts matching Chinese trading software styles (East Money, Tonghuashun).
Features
1-Day Intraday Chart: Complete trading day chart with price line, VWAP, volume bars
Multi-Day Chart: Up to 7 consecutive trading days with unified price scale
Professional Styling: Dark theme, dual Y-axis (price + percentage), red/green volume bars
Trading Hours: Correctly handles A-share trading hours (09:30-11:30, 13:00-15:00) with proper gap at lunch break
Data Source: mootdx (TongdaXin market data)
System Service: systemd support with auto-start
Related MCP server: Real-time Stock MCP Service
Screenshots
1-Day Intraday Chart

7-Day Multi-Day Chart

Installation
Prerequisites
Python 3.10+
Linux system (for systemd service)
Quick Install
git clone https://github.com/hopkdj/fenshitu-mcp.git
cd fenshitu-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txtUsage
MCP Integration
Add to your MCP client configuration:
{
"mcpServers": {
"fenshitu-mcp": {
"command": "/path/to/fenshitu-mcp/.venv/bin/python",
"args": ["-m", "fenshitu.server"],
"cwd": "/path/to/fenshitu-mcp"
}
}
}Available Tools
generate_intraday_chart
Generate a 1-day intraday chart.
Parameters:
code(required): Stock code, e.g.,"000001","600379"date(optional): Trading date inYYYYMMDDformat, defaults to todayoutput_path(optional): Output file path
Example:
{
"tool": "generate_intraday_chart",
"arguments": {
"code": "000001",
"date": "20240515"
}
}generate_multi_day_chart
Generate a multi-day intraday chart (up to 7 days).
Parameters:
code(required): Stock codestart_date(required): Start date inYYYYMMDDformatend_date(optional): End date inYYYYMMDDformat, defaults tostart_dateoutput_path(optional): Output file path
Example:
{
"tool": "generate_multi_day_chart",
"arguments": {
"code": "000001",
"start_date": "20240513",
"end_date": "20240517"
}
}HTTP Mode (Standalone)
Run as HTTP service:
export MCP_TRANSPORT=http
export MCP_HOST=0.0.0.0
export MCP_PORT=8090
python -m fenshitu.serverSystemd Service
The service is configured for auto-start:
# Enable and start
sudo systemctl enable fenshitu-mcp.service
sudo systemctl start fenshitu-mcp.service
# Check status
systemctl status fenshitu-mcp.service
# View logs
journalctl -u fenshitu-mcp.service -fChart Features
1-Day Chart
White price line + Yellow VWAP line
Red/Green volume bars (A-share convention: red=up, green=down)
Dual Y-axis: Left (price), Right (percentage change)
Time labels: 09:30, 10:30, 11:30, 13:00, 14:00, 15:00
Title with stock name, code, date, and weekday
Info bar: close price, change %, high, low, volume
Multi-Day Chart
5 trading days displayed horizontally
Unified price scale across all days
Daily price chart + volume chart
Time labels per day: 09:30, 11:30, 13:00, 15:00
Proper gap at lunch break (11:30-13:00)
Project Structure
fenshitu-mcp/
├── src/fenshitu/
│ ├── server.py # MCP server entry point
│ ├── data_fetcher.py # Data fetching (mootdx)
│ ├── chart_1day.py # 1-day chart generator
│ ├── chart_7day.py # Multi-day chart generator
│ ├── indicators.py # Technical indicators (VWAP)
│ └── styles.py # Style constants
├── pyproject.toml
├── requirements.txt
├── MCP_INTEGRATION.md # Detailed integration guide
└── README.mdDependencies
mcp>=1.20.0: MCP SDKmootdx>=0.11.0: Market data sourcematplotlib>=3.8.0: Chart renderingpandas>=2.0.0: Data processingnumpy>=1.24.0: Numerical operations
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceProvides real-time A-share (Chinese stock market) data through AKShare integration, enabling access to market overviews, company information, real-time quotes, and historical price data for Shanghai and Shenzhen stock exchanges.Last updated1Apache 2.0
- AlicenseAqualityCmaintenanceProvides real-time stock market data and analysis from Chinese markets through 34 MCP tools, including K-line charts, technical indicators, fundamental analysis, financial metrics, and market insights without requiring authentication or API tokens.Last updated3451MIT
- Flicense-qualityDmaintenanceProvides real-time quotes, fund flows, and corporate announcements for Chinese A-share stocks. It enables users to search for stocks, analyze financial indicators, and summarize quarterly reports through natural language.Last updated
- Alicense-qualityCmaintenanceReal-time A-share stock data for AI assistants. Provides real-time stock prices, K-line data, financial indicators, and sector fund flow analysis for Chinese A-share market. Multi-source data validation ensures accuracy.Last updated4MIT
Related MCP Connectors
Provide access to Chinese stock market data including historical prices, real-time data, news, and…
Read-only China A-share data for AI agents: market, limit-up, capital flow and disclosures.
Access real-time and historical market data for China A-shares and Hong Kong stocks, along with ne…
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hopkdj/fenshitu-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server