MCP Playground
A playground for MCP implementations featuring multiple microservices, including news and weather examples.
MCP Playground
Table of Contents
- Description
- Requirements
- Technologies and Tools
- Local Installation Instructions
- Available Make Commands
- Connecting with Claude Desktop
Description
This project is a playground for MCP (Model Context Provider) implementations, featuring multiple microservices including a News MCP and Weather MCP. The services are implemented using MCP with stdio transport, providing a simple and efficient way to expose functionality through standard input/output streams.
Requirements
- Python 3.12
uvpackage manager- Virtual environment support
Technologies and Tools
mcp[cli]: Model Context Provider for service communicationhttpx: Modern HTTP client for Pythonpython-dotenv: Environment variable management
Local Installation Instructions
- Clone the repository:
git clone https://github.com/RonFelsenfeld/mcp-playground.git
cd mcp-playground
- Set up the virtual environment and install dependencies:
make setup
- Activate the virtual environment:
source .venv/bin/activate
- Sync dependencies:
make sync
-
Run the MCP services:
- To run the News MCP service:
python -m src.news_mcp.main- To run the Weather MCP service:
python -m src.weather_mcp.main
Available Make Commands
make setup: Creates a new virtual environmentmake activate: Shows activation command for the virtual environmentmake sync: Syncs project dependenciesmake freeze-dependencies: Freezes current dependencies to requirements.txtmake clean: Removes virtual environment and lock files
Connecting with Claude Desktop
This project can be connected to Claude Desktop to test and interact with the MCP services using Anthropic's Model Context Protocol (MCP).
-
Install Claude Desktop, available here
-
Open Claude, go to Settings -> Developer
-
Click "Edit Config"
-
Open "claude_desktop_config.json" file
-
Copy-paste the following JSON inside the file:
{
"mcpServers": {
"weather": {
"command": "<ABSOLUTE_PATH_TO_UV>",
"args": [
"--directory",
"<YOUR_PROJECT_PATH>",
"run",
"-m",
"src.weather_mcp.main"
]
},
"news": {
"command": "<ABSOLUTE_PATH_TO_UV>",
"args": [
"--directory",
"<YOUR_PROJECT_PATH>",
"run",
"-m",
"src.news_mcp.main"
],
"env": {
"NEWS_API_KEY": "<YOUR_NEWS_API_KEY>"
}
}
}
}
Replace:
<ABSOLUTE_PATH_TO_UV>with the absolute path to youruvexecutable (from thewhich uvcommand)<YOUR_PROJECT_PATH>with the absolute path to your project directory
For the News MCP service, you'll need a News API key from newsdata.io. You can get a free API key by:
- Creating an account at newsdata.io
- Going to your dashboard
- Generating a new API key
After generating you API key, replace <YOUR_NEWS_API_KEY> with it.
Serveurs connexes
Scout Monitoring MCP
sponsorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Jira Context MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor.
Sentry
Retrieve and analyze issues, error reports, and debugging information from Sentry.io.
Interactive Feedback MCP
An MCP server for interactive user feedback and command execution in AI-assisted development.
MCP Bridge API
A lightweight, LLM-agnostic RESTful proxy that unifies multiple MCP servers under a single API.
Nova Mcp
t stores your project context, decisions, and knowledge locally in SQLite - no cloud, no telemetry. Your data stays on your machine.
Kubernetes
Kubernetes MCP server with the top30 tools
MCP Server Automation CLI
A command-line tool to automate the deployment of MCP servers to AWS ECS.
Package Version Check
Returns the latest package / dependency / tool versions for Python, NPM, Go, Docker, Helm, etc.
Random Number
Provides LLMs with essential random generation abilities, built entirely on Python's standard library.
JADX-AI-MCP
A JADX decompiler plugin that integrates with MCP to provide live reverse engineering support using LLMs.