
Connects Claude to the NIH RePORTER database, giving you access to every NIH-funded research project without authentication. Part of the Pipeworx gateway that wraps 250+ data sources behind a streamable HTTP transport. You can query projects directly or use the ask_pipeworx tool to pose questions in plain English and let the gateway figure out which calls to make. Useful when you're researching grant funding, tracking scientific initiatives, or need to pull federal research data into a workflow. Free tier available, and you can connect to just NIH RePORTER or the full Pipeworx suite depending on scope.
NIH RePORTER MCP — every NIH-funded grant, no auth.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
search_grants(query?, pi_name?, organization?, fiscal_year?, state?, ic?, limit?, offset?) — filter projects.get_project(appl_id) — full record by application ID.search_publications(pmids?, appl_ids?, core_project_nums?, limit?, offset?) — grant-linked publications.https://api.reporter.nih.gov/v2/ — public POST-JSON API, no key required.
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"nih-reporter": {
"url": "https://gateway.pipeworx.io/nih-reporter/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/nih-reporter/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 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
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 Nih Reporter data" })
The gateway picks the right tool and fills the arguments automatically.
MIT