skills/43-wentorai-research-plugins/skills/research/funding/nsf-award-api-guide/SKILL.md
Search NSF awards and grants with free public API, no auth required
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research nsf-award-api-guideInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
The National Science Foundation (NSF) Award Search API provides free, unauthenticated access to a comprehensive database of NSF-funded awards spanning decades of federally funded research in the United States. This API is invaluable for researchers seeking to understand funding trends, identify potential collaborators, or find precedent awards in their field.
The API covers all NSF directorates including Computer and Information Science and Engineering (CISE), Biological Sciences (BIO), Engineering (ENG), Geosciences (GEO), Mathematical and Physical Sciences (MPS), Social, Behavioral and Economic Sciences (SBE), and Education and Human Resources (EHR). Each award record includes principal investigator information, award amounts, abstracts, and institutional details.
No API key or authentication is needed. The service returns JSON or XML and supports a wide range of query parameters for precise filtering.
No authentication is required. The NSF Award Search API is completely open and free to use.
# No API key needed -- just make the request
curl "https://api.nsf.gov/services/v1/awards.json?keyword=quantum+computing"
GET https://api.nsf.gov/services/v1/awards.json?{params}
Key Parameters:
keyword: Full-text search across award title and abstractpiFirstName, piLastName: Filter by principal investigator nameawardeeCity, awardeeStateCode: Filter by institution locationstartDateStart, startDateEnd: Date range (format: MM/DD/YYYY)fundProgramName: NSF program nameawardeeName: Institution nameoffset: Pagination offset (default 1)printFields: Comma-separated list of fields to returnExample: Search for machine learning awards at MIT:
curl -s "https://api.nsf.gov/services/v1/awards.json?\
keyword=machine+learning&\
awardeeName=Massachusetts+Institute+of+Technology&\
printFields=id,title,piFirstName,piLastName,startDate,awardeeName,fundsObligatedAmt,abstractText&\
offset=1" | python3 -m json.tool
Retrieve details for a specific award by its NSF award number.
curl -s "https://api.nsf.gov/services/v1/awards/2345678.json?\
printFields=id,title,piFirstName,piLastName,startDate,expDate,awardeeName,fundsObligatedAmt,abstractText" \
| python3 -m json.tool
import requests
import time
base_url = "https://api.nsf.gov/services/v1/awards.json"
def search_nsf_awards(keyword, year_start, year_end, max_results=100):
"""Search NSF awards and return structured results."""
results = []
offset = 1
while len(results) < max_results:
params = {
"keyword": keyword,
"startDateStart": f"01/01/{year_start}",
"startDateEnd": f"12/31/{year_end}",
"printFields": "id,title,piFirstName,piLastName,startDate,awardeeName,fundsObligatedAmt",
"offset": offset
}
resp = requests.get(base_url, params=params)
data = resp.json()
awards = data.get("response", {}).get("award", [])
if not awards:
break
results.extend(awards)
offset += 25
time.sleep(0.5)
return results[:max_results]
awards = search_nsf_awards("large language models", 2022, 2025)
total_funding = sum(int(a.get("fundsObligatedAmt", 0)) for a in awards)
print(f"Found {len(awards)} awards, total funding: ${total_funding:,}")
for a in awards[:5]:
print(f" [{a['id']}] {a['title']} — ${int(a.get('fundsObligatedAmt', 0)):,}")
Grant Prospecting: Search for awards in your field to understand typical funding amounts, common program solicitations, and successful framing of research projects. Analyze abstracts of funded proposals for vocabulary and scope.
Collaborator Discovery: Search by keyword and explore the PI network to identify active researchers and institutions. Cross-reference with publication databases to find potential collaborators.
Funding Landscape Analysis: Track funding volumes over time for specific keywords or programs to identify emerging priorities and declining areas. Useful for strategic planning and grant writing.
Institutional Benchmarking: Compare award counts and funding totals across institutions for a given field or directorate.
offset to paginate)printFields to reduce response size and improve performancetools
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDF→Markdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it. Curated catalog of 70+ vetted projects. 支持中英文(用于「文献综述工具选型」与「一键安装/运行」)。
development
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
documentation
Use when the project collects primary data or runs a field, lab, or survey experiment, before the intervention begins — write the pre-analysis plan, size the sample from a power calculation, and register with the AEA RCT Registry. Apply after the design is chosen in aer-identification and before any outcome data are seen.
tools
Guide economists to authoritative data sources with explicit, confirmed data specifications before retrieval; interfaces with Playwright MCP to navigate portals and extract real data, not articles about data.