@pipeworx/mcp-jp-jrct
by pipeworx-io
README.md
# @pipeworx/jp-jrct
Japan Registry of Clinical Trials (jRCT), run by Japan's Ministry of Health, Labour and Welfare: search and fetch the registry's trial records, with Japanese and English titles, status, phase, condition, intervention, sponsor organisation, sites and dates.
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_jrct_search(query, status?, match?, page?, limit?)` — free-word search over the registry's records in Japanese or English (full-width and half-width forms folded). All words must match by default (`match=any` for either). Each hit gives the jRCT number, the title (cut at 30 characters by the registry's list), condition, status (pending, recruiting, suspended, recruitment_ended, complete), publication date and the record links. 50 results a page.
- `jp_jrct_get(trial_id)` — one record by jRCT number: full Japanese and English titles, status, phase, study category, condition, intervention and generic drug names, sponsor organisation (for investigator-initiated research, the coordinating investigator's affiliation, labelled as such), study type, planned sample size, number of sites listed, other countries recruiting, dates, the number the trial holds in another registry, and the public-query contact organisation and department.
Investigator and contact persons' names, e-mail addresses and telephone numbers are deliberately not returned; the record links carry what the registry publishes.
## Auth
Keyless.
## Data sources
- Ministry of Health, Labour and Welfare (Japan), Japan Registry of Clinical Trials (jRCT): read live, one request per call, nothing stored.
The registry asks that its data not be bulk-collected by program, and its front end blocks repeated automated requests for a while (HTTP 403 "Request blocked"). The pack never pages by itself; a block surfaces as a refusal naming it, not as "no trial". The registry answers an unknown trial number with an internal-error page (HTTP 500), which it also gives on a fault, so an unknown number is reported as `unknown_id_or_registry_error` rather than as a confirmed absence. The registry covers trials run in Japan; the same trial may also sit in ClinicalTrials.gov (see `other_registry`).
## Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
```json
{
"mcpServers": {
"jp-jrct": {
"url": "https://gateway.pipeworx.io/jp-jrct/mcp"
}
}
}
```
### What this endpoint actually serves
`tools/list` at `https://gateway.pipeworx.io/jp-jrct/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_jrct_search \
-H 'Content-Type: application/json' \
-d '{"query":"pembrolizumab","status":"recruiting","limit":3}'
```
No account needed for the first calls. Inspect any tool: `GET https://gateway.pipeworx.io/v1/tools/jp_jrct_search`. Find one: `POST https://gateway.pipeworx.io/v1/tools/search_packs` with `{"query":"..."}`.
## Run it from npm
`@pipeworx/mcp-jp-jrct` 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-jrct/mcp` endpoint shown above. It needs network access;
there is no offline mode.
```json
{
"mcpServers": {
"jp-jrct": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-jp-jrct"]
}
}
}
```
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 Jrct 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