# io.github.maxtechera/hushdrop (npm · hushdrop-mcp)

Open-source artifact sharing for AI agents: private, branded, zero-knowledge links.

- Trust score: 62/100 (medium)
- Change this week: +17
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `hushdrop-mcp`: 62/100 (this document), [markdown](https://verifymcp.io/servers/maxtechera-hushdrop/hushdrop-mcp.md), [page](https://verifymcp.io/servers/maxtechera-hushdrop/hushdrop-mcp)

## Channel facts

- Registry: `npm`
- Package: `hushdrop-mcp`
- Version: `0.3.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 70/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects adm-zip 0.5.18, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (105 of 109), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 40 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 723 tokens (~80/item across 9 items; 9 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 92/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 75% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add maxtechera-hushdrop -- npx -y hushdrop-mcp
```

### Codex

```bash
codex mcp add maxtechera-hushdrop -- npx -y hushdrop-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "maxtechera-hushdrop": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "hushdrop-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add maxtechera-hushdrop --command npx --arg -y --arg hushdrop-mcp
```

### Hermes

```yaml
mcp_servers:
  maxtechera-hushdrop:
    command: "npx"
    args: ["-y", "hushdrop-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "maxtechera-hushdrop": {
      "command": "npx",
      "args": [
        "-y",
        "hushdrop-mcp"
      ]
    }
  }
}
```

## 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 62, +4)

- [functional improvement] Stability: unverified → 0.23

### 2026-08-02 (score 58, +38)

- [security regression] CVE-2026-9679 affects this package: high
- [security regression] CVE-2026-1526 affects this package: high
- [security regression] CVE-2026-22036 affects this package: high
- [security regression] CVE-2026-1527 affects this package: high
- [security regression] CVE-2026-1525 affects this package: high
- [security regression] CVE-2026-39244 affects this package: high
- [security regression] CVE-2026-11525 affects this package: high
- [security regression] CVE-2026-2229 affects this package: high
- [security regression] CVE-2026-6733 affects this package: high
- [security regression] CVE-2026-12151 affects this package: high
- [security regression] Provenance: unverified → fail
- [security regression] Known CVEs: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] First check of Schema quality: unverified
- [functional] Licence: MIT

### 2026-07-31 (score 20, −7)

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

### 2026-07-30 (score 27, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 45)

First indexed and scored.

## MCP tools (9)

### `publish_html` (~171 tokens)

Publish raw HTML as a branded, password-protected (zero-knowledge AES-256) link on your own domain. Returns the URL and (if locked) the password. Locked by default.

Input parameters:

- `expire` (string): Auto-expire after this long: '7d', '24h', '2w', or a date. Enforce deletion with the host's `hush gc` cron.
- `html` (string, required): The full HTML document to publish.
- `lock` (boolean): Encrypt + password-protect (default true). Set false for a public branded page.
- `password` (string): Set a specific password. Otherwise an unguessable one is generated when locked.
- `slug` (string): Force the URL slug (e.g. 'q3-report'). Otherwise auto-generated.

### `publish_file` (~100 tokens)

Publish a file from a local path. Non-HTML files get an unguessable URL; pass page=true to wrap any file in a branded download page (optionally password-protected).

Input parameters:

- `page` (boolean): Wrap the file in a branded download page.
- `password` (string): Password-protect the download page (requires page=true).
- `path` (string, required): Absolute path to the local file to publish.
- `slug` (string)

### `update_site` (~113 tokens)

Replace the content of an existing drop in place — same URL/slug, new HTML. (Set a password to re-lock; zero-knowledge means content can't be re-keyed without re-supplying it.)

Input parameters:

- `expire` (string): Auto-expire: '7d', '24h', '2w', or a date.
- `html` (string, required): The new HTML document.
- `lock` (boolean)
- `password` (string)
- `slug` (string, required): The slug to overwrite.

### `list_sites` (~31 tokens)

List the drops currently live in your store (slug, URL, size, password if known locally, upload date).

### `delete_site` (~36 tokens)

Delete a drop (and any sibling file) by slug. Burns the artifact immediately.

Input parameters:

- `slug` (string, required): The slug to delete.

### `set_password` (~92 tokens)

Change the password gate on a hosted drop. Zero-knowledge means re-keying re-encrypts, so re-supply the HTML; returns the new URL + password.

Input parameters:

- `html` (string, required): The drop's HTML (required — content is re-encrypted under the new password).
- `password` (string): New password (auto-generated if omitted).
- `slug` (string, required): The slug to re-key.

### `set_expiry` (~71 tokens)

Set (or clear) the auto-expiry on a hosted drop. The host's gc cron deletes it after the deadline.

Input parameters:

- `expire` (string, required): '7d' | '24h' | '2w' | a date | 'off' to clear.
- `slug` (string, required)

### `set_email_gate` (~62 tokens)

Restrict a hosted drop so only viewers with a given email domain can open it (e.g. 'acme.com'); pass 'off' to remove.

Input parameters:

- `domain` (string, required): Allowed email domain, or 'off'.
- `slug` (string, required)

### `set_feedback` (~47 tokens)

Toggle the viewer feedback widget on a hosted drop (collect reactions/comments from recipients).

Input parameters:

- `enabled` (boolean): true to enable (default), false to disable.
- `slug` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/maxtechera-hushdrop/hushdrop-mcp#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 58
- 2026-08-01: 20
- 2026-07-31: 20
- 2026-07-30: 27
- 2026-07-28: 45
- 2026-07-27: 45

## Links

- npm package: https://www.npmjs.com/package/hushdrop-mcp
- Socket report: https://socket.dev/npm/package/hushdrop-mcp
- Repository: https://github.com/maxtechera/hushdrop
- Website: https://hushdrop.dev/
- Changelog RSS feed: https://verifymcp.io/servers/maxtechera-hushdrop/hushdrop-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/maxtechera-hushdrop/hushdrop-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/maxtechera-hushdrop/hushdrop-mcp