Bus Nearby MCP
Provides access to the Israeli transport API for geocoding and transit directions.
Bus Nearby MCP (Israeli transport MCP).
A Model Context Protocol (MCP) server that provides access to the Israeli transport api.
This is the Unofficial MCP of Bus Nearby API, You can check this API here
Features
https://github.com/user-attachments/assets/147ee388-e9c0-4f97-82e7-71d4d6534de0
- 🚍 Geocoding: Convert location queries to geographical coordinates
- 🗺️ Directions: Get transit directions between locations
- 🌐 Multi-language: Support for Hebrew and English
- 🔌 MCP Protocol: Standard MCP server implementation
- 📦 Docker Support: Easy deployment with Docker
Quick Start with Docker + Cursor
Prerequisites
- Cursor IDE (or any other MCP client)
- Docker Engine
Setup Instructions
-
Setup the MCP server:
{ "mcpServers": { "busnearby-docker": { "command": "docker", "args": ["run", "--rm", "-i", "shmuelc/busnearby-mcp:latest"] } } }
Connect locally with Docker
-
Clone this repo
-
Navigate to repo foler
-
Build and setup the MCP server:
docker build -t busnearby-mcp . -
Add this to mcp.json
{ "mcpServers": { "busnearby": { "command": "docker", "args": [ "run", "--rm", "-i", "--name", "busnearby-mcp-cursor", "busnearby-mcp" ], "env": {} } } }
Connect locally without Docker
Prerequisites
- Node.js 18+ installed
- npm or yarn
- Cursor IDE
Setup Instructions
-
Install dependencies:
npm install -
Build the project:
npm run build -
Test the MCP server:
npm start -
Add to your Cursor MCP configuration:
{ "mcpServers": { "busnearby": { "command": "node", "args": ["/Users/shmuel/Desktop/personal/busnearby-mcp/dist/main.js"], "env": {} } } }Important: Replace the path with your actual project path.
-
Restart Cursor to load the new MCP server
Available Tools
geocode
Convert location queries to coordinates.
Parameters:
locale: "he" or "en" (Hebrew or English)query: Location string (e.g., "תל אביב" or "Tel Aviv")
Example:
{
"locale": "he",
"query": "תל אביב"
}
directions
Get transit directions between locations.
Parameters:
fromPlace: Starting location ("address::lat,lng")toPlace: Destination ("address::lat,lng")locale: "he" or "en" (default: "he")arriveBy: Optimize for arrival time (default: false)wheelchair: Wheelchair accessible (default: false)mode: Transport modes (default: "WALK,TRANSIT")numItineraries: Number of routes (default: 3)date: Trip date (YYYY-MM-DD, optional)time: Trip time (HH:MM, optional)
Docker Commands
# Build the image
docker build -t busnearby-mcp .
# Run with docker-compose
docker-compose up -d
# Run interactively for testing
docker run --rm -i busnearby-mcp
# Test MCP protocol
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{"tools":{}},"clientInfo":{"name":"test","version":"1.0.0"}}}' | docker run --rm -i busnearby-mcp
Development
Local Development
npm install
npm run dev
Build and Test
npm run build
npm start
npm run test:e2e
Troubleshooting
Docker Issues
- Ensure Docker is running
- Try rebuilding:
docker build --no-cache -t busnearby-mcp . - Check logs:
docker logs busnearby-mcp
Cursor Connection Issues
- Restart Cursor after configuration changes
- Check MCP configuration path is correct
- Verify Docker image exists:
docker images | grep busnearby-mcp
MCP Protocol Issues
- Test server directly:
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{"tools":{}},"clientInfo":{"name":"test","version":"1.0.0"}}}' | docker run --rm -i busnearby-mcp - Check for JSON-RPC format in responses
API Reference
This MCP server interfaces with the Bus Nearby API to provide:
- Location geocoding in multiple languages
- Multi-modal transit routing
- Real-time schedule information
- Accessibility features
All responses follow standard MCP protocol formatting with proper error handling.
Contributing
Feel free to:
- 🐛 Report bugs or issues
- 💡 Suggest new features or improvements
- 📖 Improve documentation
- 🔧 Submit pull requests
Getting Started:
- Fork the repository
- Create a feature branch
- Make your changes
- Test thoroughly
- Submit a pull request
All contributions are welcome and appreciated!
संबंधित सर्वर
VelociRAG
Lightning-fast RAG for AI agents. 4-layer fusion (vector, BM25, graph, metadata), ONNX Runtime, sub-200ms search, no PyTorch.
Gemini Grounding Remote
Fetches user data and event information from the Connpass platform using the Connpass and Gemini APIs.
Google Scholar MCP
An MCP server for searching Google Scholar, built for AI assistants and automation workflows that need papers, authors, citations, and BibTeX entries.
CUFinder
Access 1B+ verified contacts and 85M+ companies for B2B lead generation, person lookup, company enrichment, and local business search directly through AI assistants.
Adzuna Job Search MCP
MCP server for Adzuna Job Search API - search jobs, analyze salaries, and research employers across 12 countries
Custom Elasticsearch
A simple MCP server for Elasticsearch, designed for cloud environments where your public key is already authorized.
MCP Naver News
Search for news articles using the Naver News API. Requires Naver News API credentials.
gemini-embedding-2-mcp
A powerful Model Context Protocol (MCP) server using gemini embedding 3 that transforms any local directory into an ultrafast, visually-aware spatial search engine for AI agents.
HexDocs MCP
Semantic search for Hex package documentation. Requires local Elixir and Mix installation.
Google Maps
An MCP server for interacting with the Google Maps API, designed for Google Cloud Run.