routes-mcp-israel
Provides real-time transit routes and arrival times for Israel, using Google Routes API, Places API, and GTFS data.
README
Routes MCP - Real-time Transit for Israel
An MCP (Model Context Protocol) server that provides real-time public transit information for Israel, combining Google Routes API, Google Places API, and GTFS data with curlbus for accurate arrival times.
Features
- Get transit routes between any two addresses in Israel
- Hebrew-localized times and addresses
- Real-time bus/train arrival information via curlbus
- Automatic city detection using Google Places API
- GTFS-based stop code matching for accurate real-time data
- Configurable number of routes returned
Google API Setup
1. Create a Google Cloud Project
- Go to Google Cloud Console
- Create a new project or select an existing one
2. Enable Required APIs
Enable these APIs in your Google Cloud project:
-
Routes API
- Go to Routes API
- Click "Enable"
-
Places API (New)
- Go to Places API (New)
- Click "Enable"
3. Create API Key
- Go to API Keys
- Click "Create Credentials" → "API Key"
- Copy your API key
- (Optional) Restrict the key to only Routes API and Places API for security
Installation
Prerequisites
- Install uv package manager
- Python 3.8+
Setup
git clone <your-repo-url>
cd routes_mcp
Configuration
Claude Desktop
Add to your Claude Desktop configuration file (claude_desktop_config.json):
{
"mcpServers": {
"routes-israel": {
"command": "uv",
"args": ["--directory", "/path/to/routes_mcp", "run", "server.py"],
"env": {
"GOOGLE_API_KEY": "your_google_api_key_here",
"MAX_ROUTES": "2"
}
}
}
}
Cursor
Add to your Cursor configuration file. The location depends on your OS:
macOS: ~/Library/Application Support/Cursor/User/globalStorage/storage.json
Linux: ~/.config/Cursor/User/globalStorage/storage.json
Windows: %APPDATA%\Cursor\User\globalStorage\storage.json
Add this configuration:
{
"mcpServers": {
"routes-israel": {
"command": "uv",
"args": ["--directory", "/path/to/routes_mcp", "run", "server.py"],
"env": {
"GOOGLE_API_KEY": "your_google_api_key_here",
"MAX_ROUTES": "2"
}
}
}
}
Note: If the file doesn't exist, create it with the above content.
Other MCP Clients
Other MCP clients use the same protocol and similar configuration.
Manual Python Installation
If you prefer traditional pip:
pip install fastmcp httpx pydantic
Then use:
{
"mcpServers": {
"routes-israel": {
"command": "python",
"args": ["/path/to/routes_mcp/server.py"],
"env": {
"GOOGLE_API_KEY": "your_google_api_key_here",
"MAX_ROUTES": "2"
}
}
}
}
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
GOOGLE_API_KEY |
✅ Yes | - | Your Google API key with Routes and Places API enabled |
MAX_ROUTES |
No | 2 |
Maximum number of routes to return (for performance) |
Usage
The server provides one tool: get_route
Example
Get transit routes from "תל אביב" to "ירושלים"
Response Format
{
"routes": [
[
{
"operator": "אגד",
"route_number": "405",
"departure_stop": "תחנה מרכזית תל אביב/קומה 3/רציף 16",
"arrival_stop": "תחנה מרכזית ירושלים/יעקב פת/רציף 15",
"departure_time": "17:16",
"arrival_time": "17:47",
"real_time_data": {
"arrivals": ["13 min", "28 min"],
"next_arrival": "13 min",
"status": "success"
}
}
]
]
}
How It Works
- Google Routes API: Gets transit directions with Hebrew localization
- Google Places API: Extracts origin city from place_id for accurate GTFS matching
- GTFS API: Finds exact stop codes based on city and station names
- Curlbus Integration: Gets real-time arrival data using GTFS stop codes
- Optimization: Only fetches real-time data for the first step of each route
Development
Running the Server
GOOGLE_API_KEY="your_key" uv run server.py
Testing Individual Components
# Test Google Routes API
curl -X POST -H 'Content-Type: application/json' \
-H 'X-Goog-Api-Key: your_key' \
-H 'X-Goog-FieldMask: routes.legs.steps.transitDetails,routes.geocodingResults' \
-d '{"languageCode":"he-IL","origin":{"address":"address1"},"destination":{"address":"address2"},"travelMode":"TRANSIT"}' \
'https://routes.googleapis.com/directions/v2:computeRoutes'
# Test Google Places API
curl -X GET -H 'X-Goog-Api-Key: your_key' \
-H 'X-Goog-FieldMask: addressComponents' \
'https://places.googleapis.com/v1/places/PLACE_ID?languageCode=he'
Logs
Monitor logs for debugging:
tail -f /tmp/routes_mcp.log
Architecture
- Google Routes API: Provides transit routing with Hebrew localization
- Google Places API: Converts place_id to city names for GTFS matching
- GTFS API: Israeli public transit stop database for accurate matching
- Curlbus: Real-time arrival data from Israeli transit operators
- Optimization: Limits to first 2 routes, real-time data only for first transit step
API Rate Limits & Performance
- Routes limited to
MAX_ROUTES(default: 2) for faster responses - Real-time data only fetched for first transit step per route
- Timeouts: 8s for GTFS lookup, 3s for real-time data
- All external API calls are properly timed out to prevent hanging
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.