Small Business Funding Finder

Search federal grants

search_grants

Read-onlyIdempotent

Search live federal funding opportunities on Grants.gov. Results come from Grants.gov, and users must confirm every detail on the official listing before applying; each result carries its listing link. Filter by keyword, applicant type (small businesses, 501(c)(3) and other nonprofits, tribes, local governments, individuals and more), category, award instrument, agency, Assistance Listing number, status (posted by default, or forecasted) and close date range. Returns the total matches and each listing with id, number, title, agency, posted and close dates, days left and URL. Sort by relevance (default with a keyword), closing_soonest (default without one) or newest. Results are cached for 10 minutes.

Input Schema

Name	Required	Description
`sort`	No
`limit`	No	Results to return, 1 to 50. Default 20.
`agency`	No	An agency code (USDA, HHS-NIH11, DOI-FWS) or name ("Fish and Wildlife", "Rural Business"). A department code includes all of its sub-agencies.
`offset`	No	Results to skip, for the next page. Default 0.
`status`	No	posted (open now, default), forecasted (announced but not yet open) or both.
`keyword`	No	Words to search for in listing titles and text, for example "rural energy" or "STEM education".
`categories`	No	Grants.gov category codes: AG Agriculture, AR Arts, BC Business and Commerce, CD Community Development, CP Consumer Protection, DPR Disaster Prevention and Relief, ED Education, ELT Employment, Labor and Training, EN Energy, ENV Environment, FN Food and Nutrition, HL Health, HO Housing, HU Humanities, IIJ Infrastructure Investment and Jobs Act, IS Information and Statistics, ISS Income Security and Social Services, LJL Law, Justice and Legal Services, NR Natural Resources, O Other, OZ Opportunity Zone Benefits, RD Regional Development, RT Recreation and Tourism, ST Science and Technology, T Transportation.
`eligibility`	No	Applicant types to match, such as small_business, nonprofit_501c3, nonprofit_other, tribal_government, city_or_township_government, individual. A listing matches when it is open to any of them.
`instruments`	No	Kinds of award to include.
`closes_after`	No	Only listings closing on or after this date, YYYY-MM-DD.
`closes_before`	No	Only listings closing on or before this date, YYYY-MM-DD.
`assistance_listing`	No	Assistance Listing (formerly CFDA) number, for example 10.868.
`include_unrestricted`	No	When eligibility is set, also include Unrestricted (code 99) listings, which are open to any applicant type. Default true.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 11, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds substantial context beyond them: data provenance (Grants.gov), the requirement that users confirm details on the official listing, per-result listing links, default status and default sort rules, and a 10-minute cache. These are exactly the behavioral traits an agent cannot get from the structured fields.

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?

Front-loaded with purpose and data source, then filters, returns, sort, and caching in a logical order. It is dense with almost no filler, though it is on the longer side for a single paragraph.

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?

With no output schema, the description properly describes the return shape (total matches plus each listing's id, number, title, agency, dates, days left, URL). Combined with 92% schema coverage and complete annotations, an agent has everything needed to call and interpret the call.

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

Parameters4/5

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

Schema description coverage is 92%, so the schema carries most parameter meaning (baseline 3). The description adds value by stating behavioral defaults the schema leaves unstated, notably that status defaults to posted and that sort defaults to relevance when a keyword is present and closing_soonest when it is not.

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

Purpose4/5

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

States a specific verb (Search) and resource (live federal funding opportunities on Grants.gov), with scope and data source made explicit. It does not name a sibling to distinguish against (e.g., grants_closing_soon or get_grant), but the filter and return detail make the purpose unambiguous.

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

Usage Guidelines3/5

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

Usage is implied through the enumerated filters and defaults (status posted by default, sort behavior with/without a keyword), but there is no explicit when-to-use-this-vs-alternatives guidance despite three sibling tools existing. An agent must infer that this is the general search versus get_grant for a single listing.

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

All Small Business Funding Finder tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?