@pipeworx/nihr
OfficialProvides access to NIHR research awards data, including ORCID identifiers for award holders.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
@pipeworx/nihr
UK NIHR MCP — every research and training award made by the National Institute for Health and Care Research: who was funded, which programme, how much, where, and which health category. Keyless.
Part of Pipeworx — an MCP gateway connecting AI agents to 1867+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
Tools
nihr_search_awards(...)— keyword search over award titles and abstracts, with filters on programme, funding stream, status, organisation, award amount and start date. Sortable by value or start date.nihr_get_award(project_id)— one award in full: both abstracts, value, dates, HRCS/UKCRC health coding, organisation with postcode and lat/lon, funding-and-awards link, and every named award holder with ORCID and role.nihr_awards_by_organisation(organisation, ...)— all NIHR awards to an institution (forgiving substring match), with total funded GBP, mean award, the organisation-name variants that matched, and a per-programme breakdown.nihr_award_holders(...)— chief investigators and co-applicants by name, ORCID or project id, returning their project ids to pivot intonihr_get_award.nihr_awards_by_programme(...)— award counts, total value, mean size and date range grouped by programme, funding stream, programme type or programme stream. Call with no arguments to discover the real programme names.
Related MCP server: NIH RePORTER MCP Server
Auth
None. The NIHR Opendatasoft portal is fully open — no key, no signup, no per-key quota.
Data sources
Portal: https://nihr.opendatasoft.com/
Dataset catalogue: UK NIHR (26 datasets)
Awards (primary, 11,502 rows):
https://nihr.opendatasoft.com/api/explore/v2.1/catalog/datasets/nihr-summary-view/recordsAward holders (12,644 rows):
https://nihr.opendatasoft.com/api/explore/v2.1/catalog/datasets/award-holders-table/recordsPublic record per award:
https://fundingawards.nihr.ac.uk/award/<project_id>
Other datasets on the same portal, not yet wired into this pack: nihr-infrastructure-supported-projects (45,258), infonihr-award-hrcs-rac-coding-and-apportionment (14,301), infonihr-award-hrcs-coding-and-apportionment (13,771), iat-data (6,275 integrated academic training), coded-portfolio (1,964), phof-datase (1,585 public health), nihr-open-data-global-health-downstream-partner-data (1,528), schools-data (1,022), rare-diseases-research-landscape-project (787), womens-health-curated-portfolio (691), prp_dataset (509).
Gotchas
project_id values come in three shapes and one of them contains slashes — 002/0028 alongside NIHR208893 and DRF-2009-02-122 — so the id must sit inside a double-quoted ODSQL literal and the whole where clause must be URL-encoded (where=project_id%3d%22002%2f0028%22); an unquoted or unencoded id silently matches nothing. limit hard-caps at 100 and Opendatasoft returns InvalidRESTParameterError rather than clamping, so the pack clamps for you. Full-text matching inside a field needs the ODS function form search(field, "text"); plain field="value" is exact equality, and field like "value" is the case-insensitive substring match this pack uses for institution and programme names — necessary because the same institution appears under several contracted names (Imperial College London, Imperial College of Science, Technology and Medicine and IMPERIAL COLLEGE HEALTHCARE NHS TRUST are three separate values covering 419 awards between them). award_amount_from_dh is a genuine number in GBP, so it can be filtered, sorted and summed — but an aggregate select with no group_by echoes the same totals row once per matched record, so read only the first result. min()/max() over a date field return full ISO timestamps rather than dates. On a group_by query total_count is the number of groups and is capped by limit, so it is not a row count. Some awards have a null programme_type (1,055 of them), and award_holder_name on the awards dataset can pack two people into one string separated by / — the award-holders dataset is the reliable per-person view.
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"nihr": {
"url": "https://gateway.pipeworx.io/nihr/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/nihr/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:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Both URLs reach the same gateway and the same 1867+ 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
curl -X POST https://gateway.pipeworx.io/v1/tools/nihr_search_awards \
-H 'Content-Type: application/json' \
-d '{"query":"dementia","project_status":"Active","min_amount":1000000,"limit":10}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/nihr_search_awards. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Run it from npm
@pipeworx/mcp-nihr 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/nihr/mcp endpoint shown above. It needs network access;
there is no offline mode.
{
"mcpServers": {
"nihr": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-nihr"]
}
}
}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 Nihr data" })The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Clinical trials, RxNorm drug lookups, FDA drug and device data, PubMed and NHS organisations.
Public fellowship and grant search with sourced details and live filter vocabularies.
Access US federal award, recipient, agency, and spending analytics data from USAspending.gov.
Immunology/virology papers, trials and grants from six databases. No API key.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides programmatic access to the NIH Reporter API for searching and retrieving detailed information on NIH-funded research projects, grants, and investigators. It enables AI assistants to query project abstracts, funding amounts, and organization details through natural language.-
- FlicenseNot gradedqualityDmaintenanceProvides tools to search and retrieve data from NIH's RePORTER grant database, enabling queries for project counts, summaries, and detailed award information.-
- AlicenseNot gradedqualityCmaintenanceAccess data on every NIH-funded research project. Free and no authentication required.81 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables searching and retrieving UK research grants, award values, institutions, and publications from the UKRI Gateway to Research API without authentication.69 npmMIT