jp-mlit-recalls
by pipeworx-io
README.md
# @pipeworx/jp-mlit-recalls
Has this vehicle maker or importer filed a recall (リコール) or an improvement
measure (改善対策) with Japan's Ministry of Land, Infrastructure, Transport and
Tourism (国土交通省)?
Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 2014+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
## Tools
- `jp_mlit_recalls_search(name?, kind?, year?, years_back?, limit?)` — filter the
ministry's public notification lists by filing company (Japanese short name as
printed, e.g. トヨタ, or a common English spelling) and kind. Each match gives the
filing date, recall or improvement measure, the companies that filed and a link
to the ministry's press release. Also returns `result` (`hit` / `no_hit`),
`total_matches`, `notifications_read`, `covers`, `individuals_dropped` and
`data_as_of`. Default scope is the latest two calendar years; one year back to
2001 or up to five latest years can be asked for.
- `jp_mlit_recalls_get(link)` — one press release: the heading with the model names,
the kind, the filing date, the filing company's full legal name and the title,
format and size of the attached documents.
## Auth
Keyless.
## Data sources
- Japan Ministry of Land, Infrastructure, Transport and Tourism (国土交通省),
notifications of motor-vehicle recalls and improvement measures. Cars, trucks,
motorcycles and work vehicles. Read from the publisher on request and held in the
serving process for an hour. `data_as_of` is the day the lists were read;
`covers.to` is the latest filing.
## Behaviour worth knowing
- The lists name filing companies, not models; model names are in each press
release's heading. The defect, number of vehicles and chassis ranges are in
attached documents that are not read; every response says so.
- Only the years read are checked, and the response lists them in `query.years_read`.
No hit means no filing by that company in those years, as read now; it does not
clear the company.
- Filers are manufacturers and importers. A name in an individual's honorific form
would be dropped and counted in `individuals_dropped`. The ministry's inquiry-office
contact details are never returned.
- A list without the expected markup, a year that parses to nothing or an HTTP failure
is refused, so a source that is down is never read as "no recall found".
## Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
```json
{
"mcpServers": {
"jp-mlit-recalls": {
"url": "https://gateway.pipeworx.io/jp-mlit-recalls/mcp"
}
}
}
```
### What this endpoint actually serves
`tools/list` at `https://gateway.pipeworx.io/jp-mlit-recalls/mcp` returns the tools in the table
above **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,
`discover_tools`, `search_within`, `remember`/`recall` and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's `initialize` response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
`ask_pipeworx`, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed
directly, instead of just this one's:
```json
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
```
Both URLs reach the same gateway and the same 2014+ data sources. The
only difference is which pack's tools are listed **directly**; `ask_pipeworx`
reaches all of them from either one.
## No MCP client? Call it over HTTP
```bash
curl -X POST https://gateway.pipeworx.io/v1/tools/jp_mlit_recalls_search \
-H 'Content-Type: application/json' \
-d '{"name":"トヨタ"}'
```
No account needed for the first calls. Inspect any tool: `GET https://gateway.pipeworx.io/v1/tools/jp_mlit_recalls_search`. Find one: `POST https://gateway.pipeworx.io/v1/tools/search_packs` with `{"query":"..."}`.
## Run it from npm
`@pipeworx/mcp-jp-mlit-recalls` is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with `npx`, and it forwards every call to the same
`https://gateway.pipeworx.io/jp-mlit-recalls/mcp` endpoint shown above. It needs network access;
there is no offline mode.
```json
{
"mcpServers": {
"jp-mlit-recalls": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-jp-mlit-recalls"]
}
}
}
```
Without a key it calls anonymously, capped at 50 calls a day. A free account
raises that to 200 a day: get a key at https://pipeworx.io/signup and add
`"env": { "PIPEWORX_API_KEY": "<your key>" }` to the server entry.
The key is sent as a Bearer token, the same way a hosted connection sends it,
so calls are metered and billed exactly as they are there.
It lists **only** this pack's tools by default. Set `PIPEWORX_META_TOOLS=1` to
also list `ask_pipeworx` and the other gateway-wide tools.
Behind an HTTPS proxy: Node's built-in `fetch` does not read `HTTPS_PROXY` by
default. Newer Node releases honour it when `NODE_USE_ENV_PROXY=1` is set; check
your Node version's documentation.
## Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English —
this works on the pack endpoint above as well as on the full gateway:
```
ask_pipeworx({ question: "your question about Jp Mlit Recalls data" })
```
The gateway picks the right tool and fills the arguments automatically.
## More
- [Docs and guides](https://pipeworx.io/docs)
- [pipeworx.io](https://pipeworx.io)
## License
MIT
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues