Skip to main content

nagoya-bus-mcp

PyPI - Version PyPI - Python Version CI

English | 日本語

Overview

Nagoya Bus MCP is a Model Context Protocol (MCP) server that lets LLMs query Nagoya City bus information. Built with FastMCP, it exposes tools and prompts for looking up bus stops, reading timetables, and checking real-time bus approach and position information. Data is sourced from the public Nagoya City bus website.

Once connected to an MCP client such as Claude Desktop, you can ask questions like "When is the next bus from Nagoya Station?" in natural language and get answers backed by live data.

Features

The server exposes the following tools:

  • get_station_number — find a bus stop number from a stop name (with fuzzy matching).
  • get_timetable — departure timetables for every route at a bus stop, organized by day of week.
  • get_approach_for_route — real-time bus positions and latest passage times along a route.
  • get_approach_for_station — real-time approaching buses for all routes at a bus stop.

It also provides prompt templates ask_timetable and ask_bus_approach for common questions.

Example queries

Bus data is in Japanese, so queries work best in Japanese:

  • 「名古屋駅のバスの時刻表を教えて」 (What's the bus timetable at Nagoya Station?)
  • 「栄のバスの接近情報を教えて」 (Show real-time bus approach info at Sakae.)
  • 「新栄町のバス停番号を教えて」 (What's the bus stop number for Shin-sakaemachi?)

Getting started

The Nagoya Bus MCP server is published to PyPI.

Claude Desktop

Add the following configuration to claude_desktop_config.json.

{
  "mcpServers": {
    "nagoya-bus": {
      "command": "uvx",
      "args": ["nagoya-bus-mcp"]
    }
  }
}

Visual Studio Code

Add the following configuration to .vscode/mcp.json.

{
  "servers": {
    "nagoya-bus": {
      "type": "stdio",
      "command": "uvx",
      "args": ["nagoya-bus-mcp"],
      "env": {}
    }
  }
}

Manual

# Using uvx
$ uvx nagoya-bus-mcp

# Using Docker
$ docker run -i --rm ghcr.io/ymyzk/nagoya-bus-mcp

For developers

# Use MCP Inspector
$ npx @modelcontextprotocol/inspector uv run nagoya-bus-mcp

# Try API client
$ uv run python -m nagoya_bus_mcp.client

Data source

This project queries the public Nagoya City bus website (https://www.kotsu.city.nagoya.jp). It is an unofficial project and is not affiliated with or endorsed by the City of Nagoya.

Release files for nagoya-bus-mcp 0.10.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for nagoya-bus-mcp 0.10.0
File Size Uploaded
nagoya_bus_mcp-0.10.0.tar.gz 175.6 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for nagoya-bus-mcp 0.10.0
File Interpreter ABI Platform
nagoya_bus_mcp-0.10.0-py3-none-any.whl Python 3 none any Details

Total release size: 193.4 kB

Release files / nagoya_bus_mcp-0.10.0.tar.gz

Download URL nagoya_bus_mcp-0.10.0.tar.gz
Size 175.6 kB
Tags Source
SHA-256 checksum
How to use checksums
725bea8c6e9b3f07eed058642f003a41742e70d04e2af28f13900c76cf4ad9d5
BLAKE2b-256 checksum
How to use checksums
4a659f4cf482f2a112812dc734455bd79603791475ddff2d0e10f8b0c74240d0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 18, 2026.

Transparency log

Release files / nagoya_bus_mcp-0.10.0-py3-none-any.whl

Download URL nagoya_bus_mcp-0.10.0-py3-none-any.whl
Size 17.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
4c707563e3d488f1b3fe55de1edc8a76e06c8986d9c41878d613505060dc0fdf
BLAKE2b-256 checksum
How to use checksums
2002e7c824d2881f2d2aaeb856334699cd0bf47d8c4ea92bde6eb336b4fa1043
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 18, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.10.0 This release

2 release files

0.9.0

2 release files

0.8.0

2 release files

0.7.0

2 release files

0.6.0

2 release files

0.5.0

2 release files

0.4.0

2 release files

0.3.2

2 release files

0.3.1

2 release files

0.2.2

2 release files

0.2.1

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page