Gachi Data API — Japan Station & Accessibility Data

Deep, obscure Japanese station, accessibility & hazard data for AI agents.

CommunityOnlineAPI key requiredGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    An API key from the service settings is required

    Deep, obscure Japanese station, accessibility & hazard data for AI agents. English-first.

    How to connect

    How to connect Gachi Data API — Japan Station & Accessibility Data to Claude

    The server address to paste into Claude settings:

    https://api.gachi-tokusuru.com/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect Gachi Data API — Japan Station & Accessibility Data to ChatGPT

    The server address to paste into ChatGPT settings:

    https://api.gachi-tokusuru.com/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect Gachi Data API — Japan Station & Accessibility Data to Cursor

    The server address to paste into Cursor settings:

    https://api.gachi-tokusuru.com/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (10)

    Raw names from tools/list. Only developers need these.

    pingConnection test / health check — call this first to confirm the server is reachable. Returns server identity, deploy version, tool count, station coverage, and the update times of the realtime layers (JMA alerts, train status) so you can confirm freshness, not just liveness. No auth, no arguments, lightweight.
    get_municipality_contextOfficial Japanese government data for any municipality, one call — housing vacancy (2003–2023), nearest-station ridership trend, hazard categories, land prices, livability counts. No scores, no judgment — official values only. Accepts a 5-digit municipality code (13104) or an exact name (Shinjuku-ku / 新宿区).
    get_station_contextSame official municipality data as get_municipality_context, resolved from a station: pass a station name (Shinjuku / 新宿 / Musashi-Kosugi) or a Japan Station Master station_id (e.g. st_00001), and it returns the context for that station's municipality. Official values only — no scores.
    get_toilet_by_stationLook up wheelchair-accessible / multipurpose toilets inside a train station, including floor, gender, equipment (wheelchair, ostomate, diaper table) and the nearest exit. Covers 526 Tokyo stations (Tokyo Bureau of Social Welfare data). Major stations outside Tokyo (Yokohama, Kawasaki, Omiya, Chiba, Fujisawa, Shin-Yokohama…) return an in-station layer that groups accessible toilets by ticket gate — inside vs outside — per railway operator. Accepts Japanese (新宿, 横浜) or romaji (Shinjuku, Yokohama) for major stations.
    get_public_toilet_by_cityList public toilets in a Japanese municipality, with wheelchair / baby-seat / ostomate flags, address and coordinates. Covers 612 municipalities nationwide (large cities capped at the top 50 results). Municipality names accept Japanese (e.g. 那覇市, 渋谷区); prefixing the prefecture improves accuracy.
    get_station_hazardOfficial disaster-risk categories at a Japanese train station, relayed live from the MLIT 不動産情報ライブラリ (Real Estate Information Library): flood inundation-depth rank, landform / liquefaction classification, and storm-surge inundation-area presence (landslide & tsunami are license-restricted and return available:false with a link to the official maps). Returns the official values/categories as-is — no composite score, no judgment. Accepts a station name in Japanese (新宿, 武蔵小杉) or romaji (Shinjuku, Musashi-Kosugi). For research/analytics; NOT a substitute for official government hazard maps or evacuation decisions.
    station_searchDiscover Japanese train stations by describing what you want around them, in English or Japanese — "朝ラーメンが食べられて車椅子トイレがある駅", "terminal station with late-night ramen", "水害リスクが低くてラーメンが多い駅". Semantic search over 9,035 station profiles (lines/terminal size, ramen density & styles, in-station accessible-toilet equipment, official hazard categories, ridership) with hybrid metadata filters — the filters guarantee the constraint, the embedding ranks by fit. Filter intent in the query text (朝ラー/深夜/おむつ/車椅子/水害リスク低…) is auto-applied (filter_source: inferred); explicit params win. Water-hazard intent (水害/洪水/浸水/高潮…リスク低) expands to flood rank AND storm-surge zone; 液状化/地盤 intent filters on the official liquefaction-tendency category; results carry risk_notes when other official hazard categories are high. Inferred facility filters with partial data coverage (おむつ/車椅子 — Tokyo-only data) BOOST confirmed stations instead of excluding unknowns (see soft_filters); explicit params remain strict. Taste/quality words (うまい, "good food", delicious…) are not evaluated (no review data); ramen ranking reflects shop density and style variety only. name_contains gives exact substring matching on station names (日本語/romaji) when the name itself is the requirement. Coverage notes: toilet stats = Tokyo stations only; ridership = Greater Tokyo operators only; hazard = official MLIT categories relayed as-is, NOT a safety judgment. Role split: station_search finds candidate stations — then get_toilet_by_station / search_ramen / get_station_hazard / get_station_context for detail on one station.
    get_active_alertsLive river flood forecasts and landslide alerts for Japan (JMA official). NOT general weather warnings (storm/heavy rain/snow) and NOT earthquakes. Covers JMA 指定河川洪水予報 (river flood forecast, levels 2–5) and 土砂災害警戒情報 (landslide warning), each with level, affected area, official summary and issue time. Optional `area` filters by 2-digit prefecture code (e.g. 13 = Tokyo) or a JMA forecast-area code. Relay of official facts — not a warning issued by this service, not a life-safety system.
    get_station_alertsLive JMA river flood forecasts and landslide alerts affecting a station's prefecture — NOT general weather warnings. Ask by station name in Japanese (新宿) or romaji (Shinjuku). Prefecture-level match (station master is Greater Tokyo). Relay of official JMA facts.
    get_train_statusLive train service status for Tokyo-area lines — delays, suspensions, resumptions. Ask 'is the Yamanote Line running?' by line or station name, English or Japanese. Status enum: normal / delayed / suspended / resumed. Cause text relayed from ODPT (English summary for known patterns, else original text + null). Data via ODPT (CC BY 4.0).