About ekidata
ekidata is a local bridge to official Japanese public data served by a hosted MCP server, aimed at agents and clients that need station, accessibility, hazard, alert, and train-status information in English. It forwards read-only tool calls without maintaining its own dataset.
Key features
- 01Municipality and station context
- 02Accessible toilet lookups
- 03Station hazard categories
- 04Live river and landslide alerts
- 05Tokyo-area train status
Use cases
- 01Find accessible toilets at a station
- 02Check official hazard data for a station
- 03Review live local alerts
- 04Look up Tokyo-area train status
MCP support
Exposes the hosted server’s tools through a local stdio MCP server and forwards calls upstream. Results pass through unchanged.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
10Saved tool list · updated 1w ago
This tool takes no parameters.
Details
From the project READMEekidata
ekidata is a small local bridge to a hosted MCP server that relays official Japanese public data in English: municipality and station context, accessible-toilet lookups, station hazard categories from MLIT data, station search, live JMA river and landslide alerts, and Tokyo-area train status.
The bridge keeps no dataset of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched. Every tool in the captured surface only reads public data.
Tools
ping— connection test and freshness check. No arguments and no required fields.get_municipality_context— official data for a municipality by 5-digit code or exact name. Required:name_or_code. Optional:fields.get_station_context— the same municipality context resolved from a station name or station_id. Its captured schema carries an empty required list, so either identifier may be supplied.get_toilet_by_station— accessible toilets inside a station, with floor, equipment and nearest exit. Required:station.get_public_toilet_by_city— public toilets in a municipality, with accessibility flags, address and coordinates. Required:city.get_station_hazard— official disaster-risk categories at a station, relayed from MLIT data. Required:station_name.station_search— find stations by describing what should be around them, in English or Japanese, with optional filters such asname_contains,pref,limit, ramen, toilet, diaper and flood-rank options. Required:q.get_active_alerts— live JMA river flood forecasts and landslide alerts. Optional:area. No required fields.get_station_alerts— those same JMA alerts for a station's prefecture. Required:station_name.get_train_status— live Tokyo-area train service status by line or station name. Required:query.
Configuration
GACHI_MCP_URL(optional) — override the upstream endpoint. Defaults tohttps://api.gachi-tokusuru.com/mcp. (The override hook is this rebuild's own labelled reconstruction.)GACHI_API_KEY(optional) — when set, every upstream request carries anAuthorization: Bearer <key>header. When it is not set, no auth header is sent. (This forwarding is also a labelled reconstruction; the original surface was captured keyless.)
Forwarding mechanics
On the first tool call the client opens a streamable
HTTP session with the upstream: a JSON-RPC initialize
request (protocolVersion 2025-03-26, clientInfo name
ekidata), then a notifications/initialized
notification, then the tools/call request carrying
the caller's arguments unchanged. When the upstream
answers initialize with an Mcp-Session-Id header,
that value rides on every later request of the session,
which is reused for the life of the process. Replies
may arrive as plain JSON or as server-sent events;
both are read.
Successful upstream results pass through verbatim,
including any isError flag the upstream sets.
Failures — a JSON-RPC error, a non-2xx status, an
unreadable response, or a request that cannot be
completed — come back as an isError result whose
text starts with ekidata error: (this rendering is
this rebuild's own labelled reconstruction).
CLI
Each tool is also a subcommand taking one JSON argument string (omit it for tools that take none):
npx @reneturcios/ekidata ping
npx @reneturcios/ekidata get_municipality_context '{"name_or_code":"13104"}'
npx @reneturcios/ekidata station_search '{"q":"terminal station with late-night ramen"}'
npx @reneturcios/ekidata get_train_status '{"query":"Yamanote"}'
npx @reneturcios/ekidata --version
Exit codes: 0 on success, 1 on an isError
result, 2 on a usage error.
MCP server
npx -y @reneturcios/ekidata mcp
MCP client config:
{
"mcpServers": {
"ekidata": {
"command": "npx",
"args": ["-y", "@reneturcios/ekidata", "mcp"]
}
}
}
Docker
docker run -i ghcr.io/cloudcorprecords/ekidata
docker run --rm ghcr.io/cloudcorprecords/ekidata --version
The container's default command is mcp, so the first
form is a stdio MCP server; any other arguments reach
the CLI normally.
Development
npm install
npm run build
npm test
npm run dev
The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.