parking-helper
Enables users to manage parking sessions, track expiration times, and retrieve real-time weather and location context via MCP tools and resources.
README
Parking Helper MCP Server (Python)
MCP server koji pomaže da vodiš evidenciju parking sesija i dobiješ kontekst (lokacija + trenutni weather).
Zašto je ovo dobar use case?
- Realan problem: lako zaboraviš kada parking ističe.
- Ima pravi datastore (SQLite) + pravi REST integracije (geocoding + weather).
- Claude može čitati resurse (Markdown izvještaj) i zvati tool-ove.
Funkcionalnosti (Minimalni zahtjevi zadatka)
- ✅ 3+ MCP tools:
start_parking– kreira sesiju (SQLite) + geocoding (Nominatim) + weather (Open‑Meteo)list_parking_sessions– lista sesije iz bazeend_parking– završava sesijucheck_expiring– (extra) šta ističe uskoro
- ✅ 1+ MCP resource:
parking://active(aktivne sesije kao Markdown)parking://expiring(sesije koje ističu uskoro)
- ✅ Eksterna integracija:
- SQLite (lokalna baza)
- REST: Nominatim + Open‑Meteo
- ✅ Claude Desktop integracija:
claude_desktop_config.jsonprimjer (copy/paste)
- ✅ README + arhitektura + upute
- ✅ Testovi:
pytest(unit testovi za DB logiku) - ⭐ Bonus: API key (opciono) + JSON structured logging
Arhitektura (ASCII)
Claude Desktop │ (MCP stdio) ▼ Python MCP Server (FastMCP) ├─ Tools │ ├─ start_parking → SQLite + Nominatim + Open‑Meteo │ ├─ list_parking_sessions → SQLite │ ├─ end_parking → SQLite │ └─ check_expiring → SQLite └─ Resources ├─ parking://active → Markdown report (SQLite) └─ parking://expiring → Markdown report (SQLite)
Instalacija
Preporuka: Python 3.10+ (idealno 3.11/3.12)
cd parking-mcp-server
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Pokreni server lokalno (ručno):
python3 server.py
Claude Desktop setup
- Otvori Claude Desktop → Settings → Developer → MCP
- U
claude_desktop_config.jsondodaj (ili kopiraj iz našeg fajla):
{
"mcpServers": {
"parking-helper": {
"command": "python3",
"args": ["server.py"],
"env": {
"PARKING_DB_PATH": "./data/parking.db",
"LOG_LEVEL": "INFO"
}
}
}
}
- Restartuj Claude Desktop.
Screenshotovi (za predaju)
Napravi 2–3 screenshot-a:
- Claude vidi server “parking-helper” u MCP listi
- Pozoveš
start_parking - Pozoveš
list_parking_sessions/check_expiring - Claude pročita resource
parking://active
Tool opis (schema + ponašanje)
1) start_parking
Input:
plate(string) – tabliceaddress(string) – adresa/lokacijaduration_minutes(int 1..1440)note(string, optional)api_key(string, optional – bonus)
Output:
id,plate,address,duration_minutes,lat,lon,weather
Error handling:
- loš input (
duration_minutes <= 0) → ValueError - geocode fail → GeocodeError → tool vrati error
- weather fail → ne ruši tool, samo vrati bez
weather
2) list_parking_sessions
Input: status (active|ended|all), limit (1..500)
Output: lista sesija
3) end_parking
Input: session_id
Output: id, status, end_time_utc
4) check_expiring
Input: within_minutes (0..1440), limit
Output: lista sesija koje ističu uskoro
Resources
parking://active→ Markdown tabela aktivnih sesijaparking://expiring→ Markdown tabela sesija koje ističu u 15 min
Bonus: API key (opciono)
Ako želiš, zaključaj server:
export MCP_API_KEY="moja-tajna"
Onda u tool pozivima proslijedi api_key.
Testovi
pip install pytest
pytest
GitHub
Kad uploaduješ:
- napravi repo public
- commitaj često (init → tools → resources → tests → readme)
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.