mcp-server

open-trading-api: Automate Trading

Name: open-trading-api: Automate Trading
Author: koreainvestment

Get a Python API for stock trading, ideal for startup founders in finance and investment.

1,552 stars813 forksPythonGuide quality 8/10Updated 7/28/2026100% free · open source

What it does

The open-trading-api provides a Python interface to interact with the Korea Investment & Securities Open API, allowing startup founders to automate stock trading operations.

When to use it

•Building a trading bot that needs to execute trades on the Korean stock market
•Developing a financial application that requires real-time stock quotes and trading functionality
•Creating a data analysis tool that needs to retrieve historical trading data from the Korean stock market

Ready-to-paste prompt

kiwoom.SendOrder('buy', 'KR0100000000', 10, 10000, '00')

Heads up: You need to have a Korea Investment & Securities account and obtain an API key to use the open-trading-api, which requires registering on the Korea Investment & Securities website and downloading the Kiwoom Open API installer to obtain the necessary credentials

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/open-trading-api && curl -fsSL https://workflowstacks.com/api/skills/open-trading-api/claude-skill -o ~/.claude/skills/open-trading-api/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How open-trading-api: Automate Trading works

Codeflow

Free to inspect

Open-trading-api: Automate Trading is a very large Python project (~183k lines across 1071 code files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, no license file, no tests found.

Size

Very large codebase

~183k lines · 1071 code files · days to read — use, don't read

Setup

One-command install

Installs like a normal app. Reading the code is optional.

Runs on

Python

No API keys detected

Python 90%TypeScript 7%C# 1%C 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
pyproject.toml
Dependencies and the commands it exposes

What's in each folder

docs/Documentation1 files

examples_llm/Folder669 files

backtester/Folder181 files

strategy_builder/Folder147 files

MCP/Folder72 files

legacy/Archived / older material51 files

stocks_info/Folder32 files

examples_user/Folder31 files

READMENo tests foundDocumentedNo CINo licenseUpdated this month