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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。