Skip to main content
Glama
grants-discovery-mcp-server

grants-discovery-mcp-server

Search Grant Opportunities

grants_search_opportunities
Read-onlyIdempotent

Search Grants.gov for U.S. federal funding opportunities by keyword, agency, eligibility, status, or category, and page through results to identify grants your organization can pursue.

Instructions

Search US federal funding opportunities on Grants.gov.

Returns one page of matches with ID, number, agency, open/close dates, and status. If more results exist, the result gives next_offset; call again with that offset. Use grants_get_opportunity with an ID for the full announcement (award sizes, eligibility, contacts).

Filter values are codes: agencies like 'HHS-NIH11' (prefix match, e.g. 'HHS'), eligibilities like '25' (use grants_list_filter_options for codes).

Examples:

  • "Open diabetes research grants" -> keyword="diabetes", statuses=["posted"]

  • "Forecasted NIH opportunities" -> agencies=["HHS-NIH11"], statuses=["forecasted"]

  • "Grants for nonprofits on rural health" -> keyword="rural health", eligibilities=["25"]

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "grants_search_opportunities"
  }
}

Input Schema

NameRequiredDescriptionDefault
alnNoAssistance Listing Number (formerly CFDA), e.g. '93.847'
limitNoResults per page
offsetNoRecords to skip, for pagination
keywordNoFree-text search over title and description, e.g. 'rural health'
agenciesNoAgency codes, e.g. ['HHS-NIH11','USDA']
statusesNoOpportunity statuses to include. Default: posted and forecasted (still actionable)
eligibilitiesNoApplicant-type codes from grants_list_filter_options, e.g. ['25']
response_formatNo'markdown' for readable text, 'json' for structured datamarkdown
funding_categoriesNoCategory codes, e.g. ['HL'] for Health

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so the bar is lower, and the description still adds real operational context: one page per call, the fields returned (ID, number, agency, dates, status), and the next_offset continuation contract. What is missing is any note on rate limits, authentication, or result-size expectations for an open-world federal API.

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

Conciseness5/5

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

It is front-loaded with the one-line purpose and return shape, then pagination, then routing to siblings, then filter-code caveats, then examples. Every line carries distinct information, and the example block is scannable rather than prose-heavy.

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?

For a 9-parameter, all-optional, no-output-schema search tool, the description covers what is returned, how to page, how to interpret codes, and where to get the full record. This is enough for an agent to invoke it correctly on the first attempt without reading the schema.

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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not encode: agencies use prefix matching (e.g. 'HHS' matches 'HHS-NIH11') and eligibilities are numeric codes that must be looked up elsewhere. The examples also demonstrate multi-parameter combinations (agencies + statuses) that clarify intended syntax.

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 first sentence names a specific verb and resource plus the data source ('Search US federal funding opportunities on Grants.gov'). It also distinguishes itself from the sibling by directing full-announcement lookups to grants_get_opportunity, so an agent can choose between the two without opening a schema.

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?

It states when to use this tool (paged search with filters) and when to use alternatives: grants_get_opportunity for full detail by ID and grants_list_filter_options to resolve code values. The three worked examples map natural-language intents to concrete parameter combinations, which removes ambiguity about how to express a query.

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