exchange_rate_MCP
Enables users to retrieve the latest USD/KRW exchange rate and receive user-friendly responses in Korean.
README
USD/KRW Exchange Rate MCP Server
This project is a small Python FastMCP server that answers questions about the USD/KRW exchange rate.
It uses this Frankfurter API endpoint:
https://api.frankfurter.dev/v2/rate/USD/KRW
When a user asks things like "USD/KRW rate?", "dollar-won exchange rate?", or "How many Korean won is 1 dollar?", an MCP client can call this server's tools and return the live result.
Files
server.py FastMCP server
requirements.txt Python dependencies
render.yaml Render Blueprint configuration
README.md Setup and deployment guide
READM.md Short pointer to README.md
MCP Tools
get_usd_krw_exchange_rate
Returns the latest USD/KRW exchange rate as structured data.
Example result:
{
"date": "2026-06-20",
"base": "USD",
"quote": "KRW",
"rate": 1532.78,
"source": "https://api.frankfurter.dev/v2/rate/USD/KRW"
}
answer_usd_krw_exchange_rate
Returns a user-friendly Korean sentence generated from the live API result.
The source code stores the Korean sentence template with Unicode escape sequences. This keeps server.py safe across Windows terminals, GitHub, and Render deployments.
Run Locally
1. Create a virtual environment
Windows PowerShell:
python -m venv .venv
.\.venv\Scripts\Activate.ps1
macOS/Linux:
python -m venv .venv
source .venv/bin/activate
2. Install dependencies
pip install -r requirements.txt
3. Start the MCP server
python server.py
Default local MCP endpoint:
http://localhost:8000/mcp
Health check endpoint:
http://localhost:8000/health
To use another port:
Windows PowerShell:
$env:PORT=9000
python server.py
macOS/Linux:
PORT=9000 python server.py
Deploy to Render
This repository includes render.yaml, so the easiest option is Render Blueprint deployment.
Option 1. Deploy with render.yaml
- Push this project to a GitHub repository.
- Open the Render dashboard.
- Click
New +. - Choose
Blueprint. - Connect the GitHub repository.
- Render will read
render.yamland create the web service.
After deployment, your MCP endpoint will look like this:
https://YOUR-RENDER-SERVICE.onrender.com/mcp
The health check endpoint will be:
https://YOUR-RENDER-SERVICE.onrender.com/health
Option 2. Create a Render Web Service manually
Use these settings:
Runtime: Python
Build Command: pip install -r requirements.txt
Start Command: python server.py
Health Check Path: /health
Render automatically provides the PORT environment variable. server.py reads that value and starts the server on the correct port.
MCP Client Setup
If your MCP client supports remote HTTP MCP servers, register this URL:
https://YOUR-RENDER-SERVICE.onrender.com/mcp
The exact client configuration depends on the MCP client you use. The important details are:
Transport: HTTP
Endpoint path: /mcp
API Source
- Frankfurter docs: https://frankfurter.dev/
- USD/KRW endpoint: https://api.frankfurter.dev/v2/rate/USD/KRW
No API key is required.
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.