Fubon MCP Server

@mingyaw

About Fubon MCP Server

No overview available yet

Config

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

{
  "mcpServers": {
    "fubon-mcp-server": {
      "command": "python3",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

Tools

No tools detected

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

Overview

What is Fubon MCP Server?

Fubon MCP Server is a Model Communication Protocol server for retrieving historical market data of Taiwan stocks (臺股). It is designed for users who need automated access to stock and ETF price history, requiring a Fubon Securities account and electronic certificate.

How to use Fubon MCP Server?

Install Python 3.8+, clone the repository, create a virtual environment, install dependencies via pip install -r requirements.txt, and set environment variables (FUBON_USERNAME, FUBON_PASSWORD, FUBON_PFX_PATH, FUBON_DATA_DIR). Start the server with python server.py and configure it in VS Code’s MCP settings under mcpServers.

Key features of Fubon MCP Server

Supports historical K‑line data for Taiwan stocks and ETFs.
Local data caching reduces API calls.
Automatically splits long date ranges into segments.
Deduplicates and sorts data.
Provides extra calculated fields (turnover, change, change percentage).

Use cases of Fubon MCP Server

Backtesting trading strategies with historical Taiwan stock data.
Building custom analytics dashboards for Taiwanese equities.
Automating daily market data downloads for internal research.

FAQ from Fubon MCP Server

What are the system requirements?

Python 3.8 or later, a Fubon Securities account/electronic certificate, and macOS, Linux, or Windows.

How is data stored and accessed?

Data is cached locally in the directory specified by FUBON_DATA_DIR. Historical data can be queried via the historical_candles tool and also via the twstock://{symbol}/historical URI across MCP.

Are there any API call limits?

Yes, the API may have daily call limits. The server handles long time ranges by automatically splitting requests into smaller segments.

What credentials are needed?

A Fubon Securities username, password, and the path to a personal .pfx certificate file. These must be kept secure and configured as environment variables.

Can I contribute to this project?

Yes, contributions via issues and pull requests are welcome. The project is licensed under MIT.

Frequently asked questions

What are the system requirements?

Python 3.8 or later, a Fubon Securities account/electronic certificate, and macOS, Linux, or Windows.

How is data stored and accessed?

Data is cached locally in the directory specified by `FUBON_DATA_DIR`. Historical data can be queried via the `historical_candles` tool and also via the `twstock://{symbol}/historical` URI across MCP.

Are there any API call limits?

Yes, the API may have daily call limits. The server handles long time ranges by automatically splitting requests into smaller segments.

What credentials are needed?

A Fubon Securities username, password, and the path to a personal `.pfx` certificate file. These must be kept secure and configured as environment variables.

Can I contribute to this project?

Yes, contributions via issues and pull requests are welcome. The project is licensed under MIT.

Comments

Basic information

More Other MCP servers

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

Inbox Zero AI

elie222

The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.

11.6K

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K