jp-umin-ctr
by pipeworx-io
README.md
# @pipeworx/jp-umin-ctr
The UMIN Clinical Trials Registry (UMIN-CTR), run by the University Hospital Medical Information Network in Japan and a WHO primary registry widely used for Japanese investigator-initiated studies: search and fetch trial records with titles, status, phase, condition, intervention, sponsor organisation, sample size and dates.
Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 2016+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
## Tools
- `jp_umin_ctr_trial_search(query, field?, page?, limit?)` — English words matched against the scientific title (default), or against the condition with `field="condition"`, or a UMIN number. Each hit gives the UMIN number, title, condition, status (pending, enrolling_by_invitation, recruiting, no_longer_recruiting, complete, suspended, terminated), disclosure date and the record link. Up to 100 results a page (`page`, `next_page`, `total_pages`).
- `jp_umin_ctr_trial_get(trial_id)` — one record by UMIN number: scientific and public titles, region, status, study type, phase, condition, intervention, primary outcome, sponsor and funder organisation, the public contact's organisation and division, target sample size, disclosure, registration, protocol, trial-start and follow-up dates, secondary identifiers and the record link. An unknown number returns `found: false`.
Investigators' and contact persons' names, e-mail addresses, telephone numbers and addresses are deliberately not returned (the registry's list column "primary person or sponsor" is not read for the same reason); the record link carries what the registry publishes.
## Auth
Keyless.
## Data sources
- University Hospital Medical Information Network (UMIN), UMIN Clinical Trials Registry (UMIN-CTR): read live, one request per search and two per record lookup, nothing stored.
This reads the registry's English-language database only, so Japanese-language queries match nothing and a study filed only in Japanese is not found; for Japan's government registry use `jp_jrct_search`. The registry gives a page count rather than a total over several pages (`total` is set only when the whole result fits one page). There is no status filter. An empty result table is reported as `found: false` with `empty_reason`.
## Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
```json
{
"mcpServers": {
"jp-umin-ctr": {
"url": "https://gateway.pipeworx.io/jp-umin-ctr/mcp"
}
}
}
```
### What this endpoint actually serves
`tools/list` at `https://gateway.pipeworx.io/jp-umin-ctr/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 2016+ 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_umin_ctr_trial_search \
-H 'Content-Type: application/json' \
-d '{"query":"pembrolizumab","limit":3}'
```
No account needed for the first calls. Inspect any tool: `GET https://gateway.pipeworx.io/v1/tools/jp_umin_ctr_trial_search`. Find one: `POST https://gateway.pipeworx.io/v1/tools/search_packs` with `{"query":"..."}`.
## Run it from npm
`@pipeworx/mcp-jp-umin-ctr` 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-umin-ctr/mcp` endpoint shown above. It needs network access;
there is no offline mode.
```json
{
"mcpServers": {
"jp-umin-ctr": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-jp-umin-ctr"]
}
}
}
```
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 Umin Ctr 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