Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.
Nothing to run from here
Federal Grant Evidence is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
7
tools declared
remote
at its publisher
—
calls last 7d
What it does
Find U.S. federal grants and return cited hard-gate and award-history evidence packs.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http utilityhouse-federal-grant-evidence-mcp https://grants.utilityhouse.xyz/mcp/registry
# 2 — ask your agent for something these tools do
# get_grant_document_manifest, analyze_nofo_requirements, compare_grant_amendments and 4 more
Federal Grant Evidence costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
UTAll 3 servers
utilityhouse3 servers
3 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http utilityhouse-federal-grant-evidence-mcp https://grants.utilityhouse.xyz/mcp/registryReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
7 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| opportunity_id | string | yes | Official Grants.gov opportunity ID, for example 332894 |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| opportunity_id | string | yes | Official Grants.gov opportunity ID, for example 332894 |
| claim_types | array | no | Optional filter; omit for every requirement class. |
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 e
| Parameter | Type | Required | Notes |
|---|---|---|---|
| opportunity_id | string | yes | Official Grants.gov opportunity ID, for example 332894 |
| since_revision | integer | no | Optional; compare only revisions after this one. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Topic or phrase such as community oral health |
| limit | integer | no | Maximum results, from 1 to 20 |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| opportunity_id | string | yes | Numeric Grants.gov opportunity id from search_federal_grants |
| organization | object | yes | — |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| request_id | string | yes | Caller-generated stable idempotency key; reuse it for retries |
| opportunity_id | string | yes | Numeric Grants.gov opportunity id |
| organization | object | yes | — |
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,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| request_id | string | yes | Caller-generated UUID used only for idempotent replay |
| opportunity_id | string | yes | — |
| profile | object | yes | — |
| attest_current_actual_non_personal_facts | boolean | yes | — |
| attest_intends_to_apply_to_opportunity_359701 | boolean | yes | — |
| consent_to_store_pointer_only_result | boolean | yes | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Federal Grant Evidence or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.3.2 · scanned 20 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest21a5e42540474ad98e1e8db2ecdb63ef3f76d2fa1e91c2fd56955436af42209f
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_grant_document_manifest | untrusted-inputexternal-sink | untrusted-input: keyword "download"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| analyze_nofo_requirements | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| compare_grant_amendments | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| search_federal_grants | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| analyze_federal_grant | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_federal_grant_evidence_pack | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| submit_federal_grant_profile_v2_beta | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest21a5e42540474ad9
Scanned2026-10-20
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.3.2.
1.3.2
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Federal Grant Evidence can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.