Federal Grants — find funding you are actually eligible for

io.github.wyattpalm2-engPublished by GitHub account wyattpalm2-engv1.0.0Updated Oct 24, 2026

Find US federal grants your organization is actually eligible to apply for. Free, no API key.

The publisher's own server: Verified Codes

VerifiedStreamable HTTPWeb executableData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Searches live U.S. federal grants on Grants.gov, filters by applicant-type eligibility, and checks prior award history.

What you can do
  • Find open federal grant opportunities filtered by an organization's applicant-type code, with deadlines, award ceilings and cost-sharing flags
  • Check whether a specific Grants.gov opportunity is eligible for a given organization type, returning eligible, ineligible or needs-review
  • Look up a program's prior awards by assistance-listing number: median award, largest award and recent recipients
When to use it
Useful for nonprofits, small businesses, universities, tribal governments and grant writers who want a shortlist of federal opportunities they can actually apply for, and a sanity check on whether a requested amount matches what a program usually funds.
Requirements
Remote streamable HTTP endpoint; no account, API key or environment variables declared. It queries the public Grants.gov and USAspending.gov APIs, so network access is needed.
Before you install
The README describes a paid tier: the top five matches are free and the full ranked list costs $2 in USDC paid to the operator's wallet and verified on-chain. Eligibility reflects entity type only; program-specific requirements still live in the announcement, and needs-review results are not a green light. Federal opportunities only.

Installation

In SourceWeft

  1. Open Federal Grants — find funding you are actually eligible for in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.wyattpalm2-eng%2Ffederal-grants/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "federal-grants-find-funding-you-are-actu": {
      "type": "http",
      "url": "https://x402-seller-m8nx.onrender.com/grants/mcp"
    }
  }
}

README

Federal Grant Fit Scanner — Grants.gov Eligibility Filter + Prior-Award Intelligence

▶ Use it free — no signup: wyattpalm2-eng.github.io/grant-fit-scanner

Runs entirely in your browser. No account, no backend, nothing uploaded or stored.

Top 5 matches free. Unlock the full ranked list for $2 in USDC — paid directly to the operator's wallet and verified on-chain in your browser. No account, no card, no processor.

Maintainer: payment setup and wallet notes are in CRYPTO.md; the card-payment alternative is in ACTIVATE.md.

Stop reading grant announcements you were never allowed to apply for.

Every other Grants.gov tool hands you a list. This one hands you a shortlist — live federal opportunities ranked by whether your specific organization can realistically win them, with the reasoning shown for every single score.

Point it at your org profile. Get back grants you are actually eligible for, that you actually have time to write, sized to what you actually need, with a read on who has been winning the money before you.


What makes this different from a Grants.gov scraper

A scraper returns rows. This returns judgment, and shows its work.

Typical Grants.gov scraperFederal Grant Fit Scanner
EligibilityDumps the raw text fieldHard mechanical gate on the federal applicant-type codes
DeadlinesPrints a dateDays remaining vs. time you need to write it
Award sizePrints a numberCompared against what you asked for
CompetitionNothingWho actually won this program before, and for how much
ScoringNone, or a black boxEvery point traced to a named fact

The eligibility gate is the whole point

Grants.gov publishes machine-readable applicant-type codes on every opportunity. A 501(c)(3) is code 12. A small business is 23. A federally recognized tribal government is 07.

This actor filters on those codes server-side, so you never even download the grants your organization is legally barred from winning. In live testing, a small business and a tribal government scanning the same database got result sets with zero overlap. That is the difference between a list and a shortlist.

It never guesses. If an opportunity publishes no applicant types, or only says "Others — see text", you get NEEDS_REVIEW, not a false green light. Absence of evidence is never reported as eligibility.

Prior-award intelligence nobody else gives you

For each opportunity's CFDA program number, the actor pulls real reported federal awards from USAspending.gov and tells you the median award, the largest, and who received them.

That single number reframes an opportunity. A $250,000 request against a program whose median prior award is $47.7M is not a good fit — it means you would be competing against major research institutions. The scanner says so, in those words, instead of quietly scoring it as a match.


Output

Every result is a ranked, CRM-ready record:

json
{  "fitScore": 79,  "band": "STRONG_FIT",  "eligibility": "ELIGIBLE",  "eligibilityReason": "Opportunity explicitly lists \"Small businesses\" (code 23) as an eligible applicant.",  "daysUntilDeadline": 65,  "title": "Advanced Development of Informatics Technologies for Cancer Research",  "agency": "National Institutes of Health",  "closeDate": "2026-10-18",  "awardCeiling": null,  "costSharingRequired": false,  "cfdaNumbers": ["93.394"],  "priorAwards": {    "medianAward": 47701808,    "sampleSize": 25,    "topRecipients": ["..."]  },  "whyThisScore": [    { "label": "Eligibility confirmed", "points": 25, "evidence": "..." },    { "label": "Comfortable runway", "points": 20, "evidence": "65 days until close." },    { "label": "Program is dominated by much larger awards", "points": 0, "evidence": "..." }  ],  "url": "https://www.grants.gov/search-results-detail/357305"}

whyThisScore is the contract: no number appears without the fact that produced it.

Verdict bands

  • STRONG_FIT (70+) — eligible, time to apply, well matched
  • POSSIBLE_FIT (45–69) — worth a look, some friction
  • REVIEW_ELIGIBILITY — you may qualify, but only prose can confirm it
  • WEAK_FIT — eligible but poorly aligned

Input

FieldDescription
organizationTypeRequired. Nonprofit, small business, university, tribal, city/county/state, school district, housing authority, individual
focusKeywordsYour mission terms, e.g. ["housing", "youth"]
requestedAmountWhat you need in USD — unlocks award-size fit and prior-winner comparison
canCostShareIf false, matching-fund requirements are penalized heavily
minDaysToApplyYour realistic prep time (default 14)
includeUnrestrictedAlso return grants open to any entity (default true)
includeIneligibleAudit what got filtered out (default false)

Who this is for

  • Nonprofits without a $299/month grant-database subscription
  • Small businesses hunting SBIR/STTR and agency funding
  • Grant writers and consultants triaging opportunities across multiple clients
  • Universities, tribal governments, municipalities, school districts, housing authorities
  • Anyone who has wasted a week on a proposal they were never eligible to submit

Data sources

Both are official U.S. government APIs serving public data. No credentials, no scraping, no terms-of-service risk, and nothing to break when a site redesigns.

Notes and limits

  • Covers federal opportunities on Grants.gov. Not state, local, or private foundation grants.
  • NEEDS_REVIEW means exactly that — the announcement text decides. Read it.
  • Prior-award data is matched by CFDA program number; programs with no award history report null rather than a fabricated benchmark.
  • Eligibility here reflects entity type. Program-specific requirements (geography, certifications, registrations) still live in the announcement.

This tool narrows the field. It does not write the proposal or guarantee an award.

Source: README.md at commit bfad96f

Tools

3

find_federal_grants

Find open U.S. federal grant opportunities an organization is ACTUALLY eligible to apply for. Filters by the machine-readable applicant-type code Grants.gov publishes on every opportunity, so ineligible opportunities are excluded rather than ranked low. Returns deadlines, award ceilings, cost-sharing requirements, and what prior winners of the same program actually received. Free, no key, live federal data.

ParameterslimitkeywordorganizationTyperequiredincludeForecasted

check_grant_eligibility

Given a Grants.gov opportunity ID and an organization type, return a definitive eligibility verdict with the reason. ELIGIBLE / INELIGIBLE / NEEDS_REVIEW. Never guesses: an opportunity that publishes no applicant types, or only 'Others (see text)', returns NEEDS_REVIEW rather than a false green light.

ParametersopportunityIdrequiredorganizationTyperequired

grant_program_history

What a federal grant program has actually awarded before, by CFDA/assistance-listing number: median award, largest award, and recent recipients from USAspending.gov. Use it to sanity-check whether a request is realistic — a $150k ask against a program with a $40M median means competing with major institutions.

Parameterscfdarequired

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Find integrations