Federal Grants — find funding you are actually eligible for

io.github.wyattpalm2-eng由 GitHub 账号 wyattpalm2-eng 发布v1.0.0更新于 Oct 24, 2026

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

发布方自己的服务:Verified Codes

已验证Streamable HTTP可网页运行数据与分析商业与电商

概览

AI 生成的概览

检索 Grants.gov 上正在开放的美国联邦资助项目,按申请机构类型筛选资格,并查询项目以往的资助记录。

可以做什么
  • 按机构的申请人类型代码查找可申请的联邦资助机会,返回截止日期、资助上限和配套资金要求
  • 针对某个 Grants.gov 机会编号和机构类型给出资格判定:符合、不符合或需人工复核
  • 按援助项目编号查询该计划以往的资助情况,包括中位金额、最大金额和近期受助机构
适用场景
适合非营利组织、小企业、高校、部落政府和资助撰写人员,用来筛出真正可以申请的联邦项目,并判断申请金额是否与该计划通常的资助规模相符。
运行要求
远程 streamable HTTP 端点;未声明需要账号、API 密钥或环境变量。它调用 Grants.gov 和 USAspending.gov 的公开 API,需要网络访问。
安装前请注意
README 提到付费层级:前五个匹配结果免费,完整排名列表需支付 2 美元 USDC 到运营者钱包并在浏览器中链上验证。资格判定只反映机构类型,项目特定要求仍需看公告;需人工复核的结果不等于符合资格。仅覆盖联邦项目。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Federal Grants — find funding you are actually eligible for,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.wyattpalm2-eng%2Ffederal-grants/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "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.

来源:README.md,提交 bfad96f

工具

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.

输入参数limitkeywordorganizationType必填includeForecasted

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.

输入参数opportunityId必填organizationType必填

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.

输入参数cfda必填

版本历史

1
  1. v1.0.0最新Sep 16, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。

其他 Find 集成