Skip to main content
Glama
Sign In

Grants Gov

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Search Historical Opportunities

search_historical_opportunities
Read-onlyIdempotent

Search Grants.gov's FULL opportunity history (closed and archived opportunities back to 2004, plus forecasted opportunities not yet posted) — coverage search_opportunities' live API cannot serve, since search2 only usefully answers "what is open right now". Covers Grants.gov's full catalog, refreshed once a day (see data_as_of). Filter by agency code, CFDA/Assistance Listing number, keyword (full-text over title + description), status, opportunity category, or post-date range. Unlike search_opportunities, status here defaults to EVERY status, not just "posted" — pass status explicitly to narrow. Answers "what did this agency fund last fiscal year", "what opportunities under CFDA 93.351 have ever closed", "what is forecasted for next year that hasn't posted yet".

Input Schema

NameRequiredDescriptionDefault
alnNoAlias for cfda.
cfdaNoAssistance Listing Number / CFDA number, exact match, e.g. "93.351". Alias: aln.
limitNoRows to return, 1-500 (default 25).
agencyNoAlias for agency_code.
offsetNo0-based start record, for paging.
statusNoposted (open now) | closed | archived | forecasted (not yet posted). One value. There is no "open" or "active" status: use "posted" for opportunities open for applications. Omit to search every status, unlike the live tool (whose default is "posted").
keywordNoFull-text search over the opportunity title and description (PostgreSQL websearch syntax — quote a phrase, "-word" to exclude). More forgiving than the live tool's exact-phrase keyword match.
agency_codeNoAgency or sub-agency code, e.g. "NIH" or "HHS-NIH11" or "DOS". Matches as a prefix/segment against the fully-qualified codes on file (same bare-vs-qualified forgiveness as search_opportunities' `agencies`). Alias: agency.
post_date_toNoOnly opportunities posted on/before this date, YYYY-MM-DD.
post_date_fromNoOnly opportunities posted on/after this date, YYYY-MM-DD.
opportunity_categoryNoSingle-letter Grants.gov category code: D discretionary, M mandatory, C continuation, E earmark, O other.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / status / description
      Previous value: -"posted | closed | archived | forecasted. Omit to search every status, unlike the live tool (whose default is \"posted\")."New value: +"posted (open now) | closed | archived | forecasted (not yet posted). One value. There is no \"open\" or \"active\" status: use \"posted\" for opportunities open for applications. Omit to search every status, unlike the live tool (whose default is \"posted\")."
    • addedInput schema / properties / status / enum
      Added value: +[
+  "posted",
+  "closed",
+  "archived",
+  "forecasted"
+]
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, open-world access, so the bar is lower; the description still adds non-obvious behavior: daily refresh cadence with a `data_as_of` field, full-catalog coverage since 2004, and the critical deviation that status defaults to all statuses rather than 'posted' like the live tool.

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 the scope claim and immediately followed by the sibling contrast and example intents. It is dense with parentheticals and repeats the coverage idea ('FULL opportunity history' / 'full catalog'), a minor redundancy, but no sentence is filler.

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

Completeness4/5

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

For an 11-parameter, no-required-parameter tool with no output schema, the description covers scope, defaults, freshness, and alternatives thoroughly. What is missing is minor: nothing about result shape or paging semantics, though offset/limit are self-documenting in 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 baseline is 3; the description adds cross-tool semantics the schema cannot — status omitting searches every status (unlike the live tool), and keyword uses a more forgiving PostgreSQL websearch syntax than the live tool's exact-phrase match. It does not restate limit/offset/date params, which the schema already documents well.

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?

States a specific verb and resource plus its exact scope: Grants.gov's full history back to 2004, closed/archived/forecasted. It explicitly contrasts with search_opportunities' live API, so the agent can distinguish it from the sibling without opening either 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?

Names the alternative (search_opportunities) and the condition that selects it ('search2 only usefully answers what is open right now'), then gives three concrete query intents ('what did this agency fund last fiscal year', 'what under CFDA 93.351 has ever closed', 'what is forecasted'). Explicit routing plus examples.

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

All Grants Gov toolsInspect
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