# Federal Grant Evidence

> Find U.S. federal grants and return cited hard-gate and award-history evidence packs.

- name: xyz.utilityhouse/federal-grant-evidence
- version: 1.3.2
- connection class: R0 (autonomous)
- trust: 92/100
- quality: 91/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/xyz.utilityhouse%2Ffederal-grant-evidence
- tools: https://api.protogrid.dev/v1/servers/xyz.utilityhouse%2Ffederal-grant-evidence/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "federal-grant-evidence": {
      "type": "http",
      "url": "https://grants.utilityhouse.xyz/mcp/registry"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-97% ~updated-43d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 91/100 (strong)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 7 of 7 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 3,067 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 7, about 3,067 tokens to load them all
- tool set hash: 62134152b3d66da8ed1390ae229edde0
- badge: [![protogrid quality](https://protogrid.dev/badge/xyz.utilityhouse/federal-grant-evidence.svg)](https://protogrid.dev/servers/xyz.utilityhouse/federal-grant-evidence)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://grants.utilityhouse.xyz/mcp/registry (streamable-http, auth none, reachable true, uptime30d 0.974359)

## Packages

_none_

## Tools (7)

- `analyze_federal_grant`: Use this when the user needs a sourced go/no-go pursuit screen for one U.S. federal grant using a non-personal organization profile and the official opportunity record. The current preview is always free and explicitly marks unresolved project relevance, document, or award-history evidence. Do not use it for discovery only, legal eligibility advice, award prediction, drafting, or submission.
- `analyze_nofo_requirements`: Use this after the document manifest, when the user needs the requirements stated inside a U.S. federal grant's official announcement — eligibility, cost share, deadlines, page limits, required submissions and evaluation criteria — each with the document, page and exact source text it came from. It returns CONFIRMED, CONFLICT, UNKNOWN or EXTRACTION_INCOMPLETE per requirement and never fills a gap with an inference. It does not determine legal eligibility, predict an award, draft, or submit.
- `compare_grant_amendments`: Use this when the user needs to know what changed between revisions of a U.S. federal grant opportunity — deadlines, cost share, eligibility, funding — with the before and after value for each change and how much it matters. It reads the official revision history and reports what Grants.gov itself declared changed alongside the computed difference. It does not read announcement documents, assess eligibility, predict an award, draft, or submit.
- `get_federal_grant_evidence_pack`: Use this limited free-beta tool after search or preview when the user wants a complete, versioned hard-gate and award-history evidence pack for one U.S. federal grant. It never requests payment during the beta. The service has a global daily beta capacity and counts only newly released complete results; reuse request_id for retries. It does not evaluate semantic project relevance, determine legal eligibility, predict an award, draft, or submit.
- `get_grant_document_manifest`: Use this when the user needs to know which official documents a U.S. federal grant opportunity has, which revision is current, and whether the official record is complete. It returns every Full Announcement, revised announcement, supporting document and application package Grants.gov holds, with official download URLs. It does not read the documents, assess eligibility, predict an award, draft, or submit.
- `search_federal_grants`: Use this when the user needs to find current or forecasted U.S. federal grant opportunities by topic. It returns official identifiers and source URLs for follow-up analysis. Do not use it to decide eligibility, predict an award, write an application, or submit anything.
- `submit_federal_grant_profile_v2_beta`: Use this opt-in free-beta tool only when the user wants to test opportunity 359701 against current actual non-personal organization, project, and readiness facts. The user must explicitly attest that the facts are current, explicitly confirm intent to apply to this opportunity, and consent to storing the resulting pointer-only pack for 30 days. The raw profile, names, contact details, identifiers, narratives, documents, and credentials are not stored. Missing facts remain NEEDS_INPUT. It does not determine legal eligibility, predict an award, draft, or submit an application.