# GrantSonar (remote · grantsonar.com)

Search verified-open US grants (federal, state, foundation). Read-only MCP for AI agents.

- Trust score: 68/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `grantsonar.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/romulusfoundry-grantsonar/api-mcp.md), [page](https://verifymcp.io/servers/romulusfoundry-grantsonar/api-mcp)

## Channel facts

- Endpoint: `https://grantsonar.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (dismiss_grant).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 967 tokens (~80/item across 12 items; 9 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http romulusfoundry-grantsonar https://grantsonar.com/api/mcp
```

### Codex

```toml
[mcp_servers.romulusfoundry-grantsonar]
url = "https://grantsonar.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "romulusfoundry-grantsonar": {
      "type": "remote",
      "url": "https://grantsonar.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add romulusfoundry-grantsonar --url https://grantsonar.com/api/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  romulusfoundry-grantsonar:
    url: "https://grantsonar.com/api/mcp"
```

### Other

```json
{
  "mcpServers": {
    "romulusfoundry-grantsonar": {
      "type": "http",
      "url": "https://grantsonar.com/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 67, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 66, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 65, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 64)

First indexed and scored.

## MCP tools (9)

### `search_grants` (~121 tokens)

Search open grant opportunities in the GrantSonar corpus (federal, state, and foundation grants). Uses semantic similarity over a plain-English description of the project or need, with a keyword fallback. Returns title, agency, deadline, award amounts, similarity score, and a GrantSonar URL per hit.

Input parameters:

- `limit` (integer): Maximum number of results (1-25, default 10).
- `query` (string, required): Plain-English description of the project, organization, or funding need (e.g. "after-school STEM programs for rural Missouri students").

### `get_grant` (~59 tokens)

Fetch the full detail of a single grant opportunity by its GrantSonar grant_id (UUID), including synopsis, eligibility, deadlines, and award amounts.

Input parameters:

- `grant_id` (string, required): GrantSonar grant UUID (from a search_grants result).

### `list_my_matches` (~97 tokens)

List YOUR organization's scored grant matches — the same personalized matches shown on your GrantSonar dashboard. Requires your API key. Returns match tier, score, reasons, pipeline status, and a URL per grant.

Input parameters:

- `limit` (integer): Max results (default 25).
- `tier` (string): Optional: only return matches in this tier.
- `view` (string): Which list (default "matches" = your active personalized feed).

### `get_my_application` (~61 tokens)

Fetch one of YOUR grant applications (status + every section draft) by application_id or grant_id. Requires your API key.

Input parameters:

- `application_id` (string): Application UUID.
- `grant_id` (string): Grant UUID — resolves your application for that grant.

### `list_my_applications` (~34 tokens)

List YOUR organization's grant applications (id, grant title, status, document type, last updated). Requires your API key.

### `save_grant` (~71 tokens)

Save a grant to YOUR pipeline, or set its status to pursuing/applied. Reversible. Requires your API key. Mirrors the dashboard Save button.

Input parameters:

- `grant_id` (string, required): Grant UUID (from list_my_matches or search_grants).
- `status` (string): Pipeline status (default "saved").

### `dismiss_grant` (~60 tokens)

Dismiss a grant from YOUR active feed, or restore it (dismissed=false). Reversible. Requires your API key.

Input parameters:

- `dismissed` (boolean): true = dismiss (default), false = restore.
- `grant_id` (string, required): Grant UUID.

### `update_application_section` (~131 tokens)

Write content into one section of YOUR grant application (replace or append). Requires your API key. The prior draft is snapshotted to version history first, so this is recoverable. Use get_my_application to see section_keys.

Input parameters:

- `application_id` (string, required): Application UUID (from list_my_applications).
- `content` (string, required): The text/HTML to write into the section.
- `mode` (string): replace (default) overwrites; append adds to the end.
- `section_key` (string, required): Which section to write (e.g. "statement_of_need"). See get_my_application.

### `draft_application_section` (~141 tokens)

Generate an AI first-draft for one section of YOUR application, grounded in the funding notice and your org profile, and save it into that section (prior content snapshotted first). Requires a paid API key. This is the only tool that runs the grant writer, so it is metered heavily. Returns the drafted text. Use get_my_application for section_keys.

Input parameters:

- `application_id` (string, required): Application UUID.
- `document_type` (string): Draft a short Letter of Inquiry ("loi") or a full section ("full"). Defaults to the application's submission stage.
- `section_key` (string, required): Which section to draft (see get_my_application).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/romulusfoundry-grantsonar/api-mcp#diagnostics

## Score history

- 2026-08-03: 68
- 2026-08-02: 67
- 2026-08-01: 67
- 2026-07-31: 67
- 2026-07-30: 66
- 2026-07-29: 66
- 2026-07-28: 66
- 2026-07-27: 65
- 2026-07-26: 64

## Links

- Remote endpoint: https://grantsonar.com/api/mcp
- Repository: https://github.com/romulusfoundry/grant-radar
- Changelog RSS feed: https://verifymcp.io/servers/romulusfoundry-grantsonar/api-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/romulusfoundry-grantsonar/api-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/romulusfoundry-grantsonar/api-mcp