
Upbit MCP Server
Enables interaction with the Upbit cryptocurrency exchange through public market data tools and optional private trading tools. Supports getting ticker data, orderbooks, trades, account information, and executing trading operations through natural language.
README
Upbit MCP Server (TypeScript)
Fast MCP server for interacting with Upbit. Provides public market data tools and optional private trading tools.
Requirements
- Node.js 18+
- pnpm 8+
Install
pnpm install
Environment
Copy and edit .env
:
cp .env.example .env
.env.example
:
UPBIT_SERVER_URL=https://api.upbit.com
UPBIT_ACCESS_KEY=
UPBIT_SECRET_KEY=
UPBIT_ENABLE_TRADING=false
Private tools require UPBIT_ACCESS_KEY
, UPBIT_SECRET_KEY
, and UPBIT_ENABLE_TRADING=true
.
Where to get Upbit API keys
Before you begin, you need to get your Upbit API keys:
- Create an account on Upbit if you don't already have one
- Go to the Upbit Developer Center
- Create a new API key
- Make sure to set appropriate permissions (read, trade, withdraw as needed)
- Store your API keys(
UPBIT_ACCESS_KEY
,UPBIT_SECRET_KEY
) in the.env
file (see Installation section) setUPBIT_ENABLE_TRADING=true
to enable private tools.
Build & Run
pnpm run build
pnpm run start
For easier testing use this (in project root):
pnpm run build
npx @modelcontextprotocol/inspector node dist/index.js
If installed globally or via npx, you can also run the bin:
mcp-upbit-server
Runs over stdio for MCP clients.
Tools
Public:
GET_TICKER
— latest ticker for a market. Params:{ "market": "KRW-BTC" }
GET_ORDERBOOK
— orderbook snapshot. Params:{ "market": "KRW-BTC" }
GET_TRADES
— recent trades. Params:{ "market": "KRW-BTC" }
Private (requires env and enable flag):
GET_ACCOUNTS
GET_ORDERS
—{ market?, state?, page?, limit? }
GET_ORDER
—{ uuid? , identifier? }
CREATE_ORDER
—{ market, side, ord_type, volume?, price? }
CANCEL_ORDER
—{ uuid }
All tool outputs are JSON strings for easy display.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.