Research Funding Landscape MCP Server
Pricing
from $50.00 / 1,000 tool calls
Research Funding Landscape MCP Server
Answer 'who funds research on this topic' across two public government registers: US National Science Foundation awards and UK Research and Innovation's Gateway to Research.
Pricing
from $50.00 / 1,000 tool calls
Rating
0.0
(0)
Developer
NexGen Watch
Maintained by CommunityActor stats
0
Bookmarked
1
Total users
0
Monthly active users
a day ago
Last modified
Share
Answer "who funds research on this topic" across two public government registers — the US National Science Foundation awards API and UK Research and Innovation's Gateway to Research — live.
Built for grant writers and research-development teams.
Five things this server gets right that a naive read gets wrong
Every one measured live against the sources on 2026-07-30.
1. UKRI treats a multi-word topic as OR, not as a phrase — the error is 15×
term=quantum 5,835 recordsterm=computing 14,453 recordsterm=quantum computing 18,219 records <- the union of the two, not the phraseterm="quantum computing" 1,182 records <- the phrase
An unquoted two-word topic returns roughly fifteen times too many projects, most about neither subject together. This server quotes a multi-word topic by default and reports both counts in every answer, so the size of the difference is visible rather than taken on trust.
2. UKRI answers "no results" with HTTP 404
term=zzzqqqnotarealterm -> HTTP 404, Link-Records: 0
That is the register saying nobody here funds that — an answer, not a failure. This server
returns it as a real empty result and charges for it. A 404 without Link-Records: 0 is
a route failure and raises.
3. NSF's keyword matches the abstract, not the title
Measured on ten hits for "quantum": six carried the word nowhere in the title, including "REU Site: Extremal Graph Theory and Dynamical Systems at RIT". Correct behaviour, and misleading if you assume otherwise — so every award reports whether the topic is visible in its title, and each search reports the ratio.
4. An unrecognised NSF parameter returns zero rows, not an error
title=quantum -> totalCount 0 (an unrecognised parameter)keyword=quantum -> totalCount 519 (the real one)
A typo therefore answers "nobody funds this". Only parameter names proven real against the live API are ever sent, and the data layer refuses anything else with a named reason.
5. NSF's offset is 0-based
offset=1 returns totalCount − 1 records and drops the first one, every time, on every
query. Every walk here starts at 0.
The two registers are shaped differently, and are never merged
On NSF the funder is always the National Science Foundation, so ranking by funder collapses the whole US side into one row and answers nothing. The comparable unit is the funding programme. On UKRI the comparable unit is the council or scheme — EPSRC, Innovate UK, STFC, UKRI FLF.
find_funders reports the unit and says which kind it is. US amounts are USD, UK amounts
are GBP, and they are never added together.
Tools
| tool | what it answers |
|---|---|
find_funders | Who funds this topic — funding units across both registers, ranked, with counts and totals per currency |
list_us_awards | NSF awards matching a topic, with programme, recipient, PI, dates and amount |
list_uk_projects | UKRI-funded projects matching a topic, with the council or scheme behind each |
explain_limits | What this server will and will not say, and the five traps above. Read before acting. |
Scope
Two registers only: NSF and UKRI. NIH, DOE, DOD, ERC, Horizon, charitable and industrial funders are not covered — "who funds this" here means "who among these two registers has funded it".
Neither host publishes a robots.txt and neither states a rate limit, so pacing is our own
choice: each source has its own strict-pacing bucket at 2 requests/second.
Rankings are over the sample actually read, not the whole matching set; every answer carries the full match count alongside the sample size.
This server reports who has funded work matching a topic. It does not say who will fund you, does not rank funders by suitability, and never mixes currencies.
Pricing
| Event | Price |
|---|---|
Server start (apify-actor-start) | $0.05, charged once per server run by the platform |
Tool call (mcp-tool-call) | $0.05 flat per completed tool call |
No other events. Memory is pinned to 1024 MB so the start fee is charged once — on this platform the start event bills once per gigabyte.
Errors and notices are not charged. An empty topic, an unknown source name, or a read failure on every requested register returns without billing.
A sourced "nobody funds this" IS charged — including UKRI's 404-with-zero-records, which is that register's way of saying it.
If one register fails and the other answers, you get the answer and the named failure — a partial read never looks like a complete one.
If a tool call cannot be billed correctly, the call fails rather than serving free.