Advanced MCP Server
This Advanced MCP Server provides AI assistants with real-time data access and local system exploration capabilities through three main tools:
๐ฆ๏ธ Weather Alerts - Fetch active weather alerts for any US state using two-letter state codes (e.g., 'CA', 'NY', 'TX') via the National Weather Service
๐ฐ News Search - Search for recent news articles on specific topics using NewsAPI with real-time results
๐ Directory Explorer - List and explore local filesystem directories safely, defaulting to the current directory
Deployment & Testing: Can be deployed to cloud services like Railway with secure API key management via environment variables. Includes both local stdio testing and online SSE testing options for different development scenarios.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Advanced MCP Server show me active weather alerts for California"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
๐ Advanced MCP Server
A professional Model Context Protocol (MCP) server built with Python and FastMCP. This server extends AI capabilities by providing real-time data and local system access.
โจ Features
๐ฆ๏ธ Weather Alerts: Fetches active US weather alerts from the National Weather Service.
๐ฐ News Search: Real-time news searching using the NewsAPI.
๐ Directory Explorer: Allows the AI to list and explore local system directories safely.
๐ Secure Secrets: Uses
.envfor safe API key management.
Related MCP server: Weather MCP Server
๐ ๏ธ Getting Started
Prerequisites
Python 3.10+
uv (Recommended)
Installation
Clone the repository:
git clone https://github.com/Rahii123/mcp.git cd mcpInstall dependencies:
uv sync
Setup
Create a .env file in the root directory and add your NewsAPI key:
NEWS_API_KEY=your_actual_key_here๐ Running the Server
Run directly with uv:
uv run server.py๐งช Testing Your Server
We have provided two separate clients for testing:
๐ 1. Local Testing (Stdio)
Use this when you are developing on your own machine.
uv run client_local.pyThis starts the server as a background process and communicates directly.
๐ 2. Online Testing (SSE)
Use this after you have deployed your server to the web (e.g., Railway).
uv run client_online.pyThis asks for your deployment URL and connects over the internet.
โ๏ธ Deployment to Railway (Step-by-Step)
1. Push to GitHub
Ensure all your changes are committed and pushed to your GitHub repository:
git add .
git commit -m "Prepare for deployment"
git push origin main2. Connect to Railway
Go to Railway.app and log in.
Click + New Project > Deploy from GitHub repo.
Select your
mcprepository.
3. Configure the Service
Environment Variables:
Go to the Variables tab in Railway.
Add
NEWS_API_KEY:(Your actual NewsAPI Key)
Start Command:
Railway should automatically detect
pyproject.toml, but if needed, set the start command to:uv run server.py
Networking:
Railway will automatically detect the port from the
$PORTenvironment variable. Ensure yourserver.pyis usingmcp.run(transport='sse')(I've already configured this for you).
4. Fetch your URL
Once the build is finished, Railway will provide a public URL (e.g., https://mcp-production.up.railway.app).
The MCP endpoint will be at: https://your-app-url.up.railway.app/sse
Available Tools
3 toolsget_weather_alertsB
Fetch active weather alerts for a given US state (e.g., 'CA', 'NY').
Inputs: state (required). Returns: result
list_directoryB
List the contents of a local directory. Default is current directory.
Inputs: path. Returns: result
search_newsB
Search for recent news articles on a specific topic.
Inputs: query (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: get_weather_alerts targets weather data for US states, list_directory handles local file system operations, and search_news retrieves news articles. There is no overlap in functionality or ambiguity between these tools.
The naming is mixed: get_weather_alerts and search_news follow a verb_noun pattern, but list_directory uses a verb_noun format that is slightly different in structure. While readable, the conventions are not fully consistent across all tools.
With only 3 tools, the server feels thin and under-scoped for an 'Advanced MCP Server', suggesting a lack of depth or comprehensive coverage. This low count may limit the server's utility for complex tasks.
The tool surface is severely incomplete, as the tools cover unrelated domains (weather, file system, news) without a coherent purpose. There are significant gaps in each domain, such as no update or delete operations, making it hard for agents to perform full workflows.
Maintenance
Related MCP Connectors
US NWS weather alerts and 5-day forecasts for AI agents. $0.01 per call.
US weather & geo for AI agents: forecasts, alerts, earthquakes, elevation, geocoding. No keys.
US weather & geo for AI agents: forecasts, alerts, earthquakes, elevation, geocoding. No keys.
Get US weather forecasts, active and recent alerts, and current observations.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI assistants to access real-time US weather forecasts and alerts through the National Weather Service API.2ISC
- FlicenseBqualityDmaintenanceProvides real-time US weather alerts and forecasts by integrating with the National Weather Service API. It enables AI assistants to fetch state-specific alerts and detailed local forecasts using geographic coordinates.21-
- FlicenseNot gradedqualityDmaintenanceProvides real-time weather alerts and forecasts from the National Weather Service for US locations, integrating with AI assistants via the Model Control Protocol.-
- AlicenseNot gradedqualityDmaintenanceProvides weather forecasts and alerts for US locations via the National Weather Service API, enabling AI assistants to deliver real-time weather information.28 npmISC