Skip to main content
Glama
cliwant

mcp-sam-gov

by cliwant

nsf_search_awards

Read-only

Search NSF research grant awards by keyword, state, organization, UEI, or principal investigator. Retrieve award details including amounts and dates.

Instructions

Search awarded NSF research-GRANT awards (keyless; api.nsf.gov/services/v1/awards.json) — the NEW federal research-funding recipient-enrichment axis (who receives NSF research money, by organization / UEI / PI / state, joinable to SAM/USAspending via ueiNumber/parentUeiNumber). The grant-SIBLING of nih_reporter_search_projects on a different agency. LIVE-CONFIRMED-narrowing filters ONLY, module-built into a URLSearchParams query (NO raw passthrough): keyword (free text; MULTI-WORD is OR-tokenized — 'machine learning' = machine OR learning, disclosed in _meta.notes), awardeeStateCode (UPPERCASE 2-letter USPS enum — the SSRF + silent-zero guard; a non-state typo silently returns 0), awardeeName, ueiNumber (12-char UEI — an EXACT SAM/USAspending join), parentUeiNumber (parent-org roll-up), pdPIName, dateStart/dateEnd (STRICT mm/dd/yyyy on the award ACTION date — a wrong format is silently mis-parsed), limit (1..100, def 25 → rpp), offset (0..9999). Returns { awards:[{ id, title, agency, cfdaNumber, transType, awardee:{ name, city, stateCode, ueiNumber, parentUeiNumber }, performanceSite, principalInvestigator:{ fullName, firstName, lastName, middleInitial, email, id }, coPrincipalInvestigators, programOfficer, amounts:{ fundsObligatedAmt, estimatedTotalAmt, fundsObligatedByYear }, dates, program, activeAward, historicalAward }] } (abstract EXCLUDED — use nsf_get_award) + honest _meta. HONESTY: NSF Awards are RESEARCH GRANTS, NOT procurement contracts (ueiNumber joins to SAM/USAspending but the award nature differs — disclosed every response); totalAvailable = the EXACT metadata.totalCount below 10,000 and SATURATES at 10,000 (an ES track_total_hits cap ⇒ totalIsLowerBound:true + a note — the true total is ≥10,000 and only the first 10,000 are retrievable); NSF caps keyless retrieval at offset+rpp ≤ 10,000 (offset ≥ 10,000 ⇒ invalid_input; the outgoing rpp is clamped so a page never crosses the window). fundsObligatedAmt/estimatedTotalAmt arrive as STRINGS → number|null (a real $0 is 0, absent is null). Genuine-empty (totalCount:0) ⇒ complete:true/total:0; a serviceNotification at HTTP 200 (bad param / deep offset) ⇒ invalid_input/upstream_unavailable THROWS (never a fake empty); an outage/5xx/timeout THROWS; a 200 body that isn't {response:{award,metadata}} or a non-numeric totalCount ⇒ schema_drift. Feed a row's id to nsf_get_award for the full record + abstractText.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoAwards per page (→ NSF rpp), 1..100, default 25. The OUTGOING page size is clamped so offset+rpp ≤ 10,000 (crossing NSF's retrieval window triggers a FATAL).
offsetNo0-based offset. HARD-CAPPED at 9,999: NSF caps keyless retrieval at the first 10,000 records (offset+rpp ≤ 10,000), so offset ≥ 10,000 is refused (invalid_input) — narrow criteria to bring the set under 10,000.
dateEndNoAward ACTION-date upper bound. STRICT mm/dd/yyyy (same semantics/foot-gun as dateStart). e.g. '12/31/2024'.
keywordNoFree-text search over title/abstract. NOTE: NSF OR-tokenizes a MULTI-WORD keyword (matches ANY word, not the phrase — 'machine learning' = machine OR learning, a far broader set; disclosed in _meta.notes). Use a single distinctive word or add a scoping filter for a precise set.
pdPINameNoPrincipal-investigator name filter (2..120 chars). LIVE-CONFIRMED to narrow. e.g. 'Bell'.
dateStartNoAward ACTION-date lower bound (the initial award/obligation date, NOT the project startDate — live-verified). STRICT mm/dd/yyyy; a wrong format (yyyy-mm-dd) is silently mis-parsed by NSF (not an error), so it is rejected. e.g. '01/01/2024'.
ueiNumberNoAwardee UEI — a 12-char alphanumeric SAM/USAspending Unique Entity ID (uppercase-normalized before sending). LIVE-CONFIRMED an EXACT recipient-graph filter (the clean SAM/USAspending join). e.g. 'FTMTDMBR29C7' (Johns Hopkins).
awardeeNameNoAwardee-organization name filter (2..200 chars). LIVE-CONFIRMED to narrow (a top recipient like 'Johns Hopkins University' may still saturate at the 10,000 count cap).
parentUeiNumberNoParent-organization UEI — a 12-char alphanumeric UEI for the awardee's parent entity (uppercase-normalized). LIVE-CONFIRMED an EXACT narrow (the parent-org roll-up join). e.g. 'GS4PNKTRNKL3'.
awardeeStateCodeNoAwardee-organization US state/territory 2-letter USPS code (UPPERCASE — the enum is the SSRF value guard + the silent-zero guard: a non-state typo silently returns 0 awards on NSF, indistinguishable from 'no NSF funding', so it is an invalid_input). LIVE-CONFIRMED to narrow. e.g. 'CA'.
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description extensively discloses behavioral traits beyond annotations: NSF caps retrieval at 10,000 records (totalIsLowerBound), OR-tokenization of keywords, strict date format with silent mis-parsing, SSRF guard on state code, funds as strings, error handling (serviceNotification, schema_drift, outages). No contradiction with annotations (readOnlyHint, openWorldHint).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but highly information-dense. It is front-loaded with purpose and uses bold for key terms. Every sentence earns its place, but it could be more streamlined. Minor verbose phrases like 'LIVE-CONFIRMED-narrowing filters ONLY' could be simplified without losing meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description fully details the return structure (awards array with fields, _meta, error conditions, saturation behavior, and link to nsf_get_award). It covers limitations (10k cap), data types (strings to numbers), and edge cases (genuine empty vs. bad param). It is as complete as needed for reliable invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 100% schema coverage, the description adds substantial meaning: for keyword, it explains OR-tokenization and recommends single words; for offset, it explains the hard cap and invariant; for dateStart/dateEnd, it warns about format foot-gun; for ueiNumber, it clarifies exact SAM join. Each parameter's description provides practical context and edge cases beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches awarded NSF research-grant awards, explicitly distinguishes it from sibling tools (nih_reporter_search_projects for grants, nsf_get_award for full records), and provides the specific API endpoint. The verb 'search' and resource 'NSF research-grant awards' are precise and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance: it is the grant counterpart of nih_reporter_search_projects; when to use narrowing filters to avoid the 10,000 cap; warns against multi-word keyword OR-tokenization; advises feeding a row's id to nsf_get_award for abstracts; and explains limitations like the silent-zero guard on state codes. It helps the agent decide between this and alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cliwant/mcp-sam-gov'

If you have feedback or need assistance with the MCP directory API, please join our Discord server