한국투자증권 REST API MCP (MCP)

@MCP-Mirror

代码仓库

基本信息

分类

开发工具

传输方式

stdio

作者

MCP-Mirror

关于 한국투자증권 REST API MCP

Mirror of

#migusdn#kis#mcp #server #rest-api #stock-trading

한국투자증권 REST API MCP 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "migusdn_KIS_MCP_Server": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

한국투자증권 REST API MCP 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is 한국투자증권 REST API MCP (Model Context Protocol)?

한국투자증권 REST API MCP (Model Context Protocol) is a server that uses the Korea Investment & Securities (KIS) REST API to provide stock trading and market data inquiry via the Model Context Protocol. It supports domestic and overseas stock trading, price checks, account management, and is intended for developers building AI‑assisted trading tools.

How to use 한국투자증권 REST API MCP (Model Context Protocol)?

Install Python 3.13+ and uv, then create a virtual environment and install dependencies with uv pip install -e .. Set the environment variables KIS_APP_KEY, KIS_APP_SECRET, KIS_ACCOUNT_TYPE, and KIS_CANO with your KIS API credentials. The server exposes MCP tools such as inquery_stock_price, order_stock, inquery_balance, order_overseas_stock, and others for trading and data retrieval.

Key features of 한국투자증권 REST API MCP (Model Context Protocol)

🇰🇷 Domestic stock trading: price, orders, balance, ask prices, order history
🌏 Overseas stock trading: US, Japan, China, Hong Kong, Vietnam
Real‑time price and execution information
Asynchronous processing for fast responses
Reliable error handling and extensible design
Environment‑variable configuration for API keys and account

Use cases of 한국투자증권 REST API MCP (Model Context Protocol)

Automate domestic stock buy/sell orders via AI agents
Retrieve real‑time overseas stock prices for portfolio monitoring
Check account balance and profit/loss status programmatically
Inquire daily order history and order details for reconciliation
Fetch ask price (bid/ask depth) for trading decisions

常见问题

What is the difference between this server and using KIS API directly?

This server wraps the KIS REST API into the Model Context Protocol, enabling AI assistants to call trading and data functions through a standardized interface. It handles authentication, async responses, and error formatting.

What are the runtime requirements?

Python 3.13 or later and the uv packaging tool are required. Dependencies are installed via `uv pip install -e .`.

Where do user credentials and trading data reside?

API keys and account information are set as environment variables (`KIS_APP_KEY`, `KIS_APP_SECRET`, `KIS_ACCOUNT_TYPE`, `KIS_CANO`). All trading data is retrieved from and sent to the Korea Investment & Securities API; no data is stored locally.

Are there any known limits or restrictions?

The project is still under development. API call limits from KIS apply, and trading is only available during market hours (domestic 09:00–15:30 KST; overseas hours vary by market). Use a virtual account for testing before real trading.

How is authentication handled?

Authentication uses a REST API app key and secret key, passed via environment variables. No OAuth flow is implemented; the server uses these keys directly for every API call.

开发工具分类下的更多 MCP 服务器

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

NextBlock CMS

NextBlock

Open-source Next.js + Supabase CMS with a per-site MCP server: scaffold a site, then create pages, posts, navigation, media and SEO from Claude, Cursor or any MCP client. Streamable HTTP with a bearer token you mint in y

LastPing

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

SSH MCP Server

hypnosis

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.