# snapWONDERS Vaultify (remote · snapwonders.com)

Hosted snapWONDERS MCP: hide files in images, reveal hidden content, analyse media, convert formats

- Trust score: 68/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

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

## Channel facts

- Endpoint: `https://snapwonders.com/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 2026-10-23.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 19 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 76/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2445 tokens (~128/item across 19 items; 19 tools + 0 resources), over budget; trim descriptions and params.
  - 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 19 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 19 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### How do I install the snapWONDERS Vaultify MCP server?

snapWONDERS Vaultify is a hosted endpoint at https://snapwonders.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-snapwonders-mcp 'https://snapwonders.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-snapwonders-mcp": {
      "url": "https://snapwonders.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-snapwonders-mcp": {
      "type": "http",
      "url": "https://snapwonders.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-snapwonders-mcp]
url = "https://snapwonders.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-snapwonders-mcp --url 'https://snapwonders.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-snapwonders-mcp:
    url: "https://snapwonders.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-snapwonders-mcp": {
      "Transport": "http",
      "Url": "https://snapwonders.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-snapwonders-mcp -t streamable-http -u 'https://snapwonders.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-snapwonders-mcp": {
      "type": "http",
      "url": "https://snapwonders.com/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.

### 2026-10-23 (score 68, +1)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 19 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Endpoint reachability: unreachable → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.27

### 2026-10-22 (score 67, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.20 → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes.
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-10-20 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-18 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 65, +1)

- [security improvement] Injection markers: unverified → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 19 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Endpoint reachability: unreachable → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.07

### 2026-10-16 (score 64, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] Tool safety: pass → unverified
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes.
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-10-15 (score 64)

First indexed and scored.

## MCP tools (19)

### `status` (~23 tokens)

Returns the current health status of the Vaultify service. No API key required.

### `vaultify_get_started` (~85 tokens)

Introduction to snapWONDERS Vaultify steganography: what it does, how AES-256 + Argon2id + LSB embedding works, a pre-computed sample hide result showing the exact response schema, and guidance on creating a free account and API key to start using the API. No API key required — call this first to understand the Vaultify workflow.

### `snapwonders_get_started` (~73 tokens)

Introduction to snapWONDERS forensic analysis and media conversion: what each service does, pre-computed sample analyse and convert results showing the exact response schemas, and guidance on creating a free account and API key. No API key required — call this first to understand the snapWONDERS analyse and convert workflows.

### `vaultify_session_create` (~175 tokens)

Creates an upload session for hide (conceal a file inside a cover image/video) or reveal (extract hidden content from a stego image/video) processing. Returns the upload_uid and upload instructions. Upload each file with a single POST /api/upload carrying the file as the request body (hide needs X-Upload-Step 1 for the secret and 2 for the cover); its response reports ready_for_job_start, so no separate verification call is needed. Direct upload accepts files up to max_upload_bytes (returned in this response, currently 95 MB); anything larger must use the resumable TUS endpoint at /api/tus. Requires X-Api-Key header.

Input parameters:

- `type` (string, required): hide: conceal content inside a cover image or video; reveal: extract hidden content from a stego image or video

### `vaultify_session_files` (~61 tokens)

Lists all files currently uploaded for a stego session. Check that all files show status "completed" before calling vaultify_job_start. Requires X-Api-Key header.

Input parameters:

- `upload_uid` (string, required): The upload_uid returned by vaultify_session_create

### `vaultify_job_start` (~503 tokens)

Submits options and queues a hide or reveal job for a session whose files have all been uploaded. Hide jobs support the full set of encoding options; reveal jobs only use upload_uid, password, and expiry. The call is idempotent. Requires X-Api-Key header.

Input parameters:

- `expiry` (string, required): How long the result download link remains accessible after the job completes. Free-tier keys are silently clamped to upload.free_max_expiry (default 1d); Pro accounts get the requested value.
- `output_format` (string): Hide only. Image format for stego output. All formats are lossless. Default: avif.
- `packing_strategy` (string): Hide only. How secrets are distributed across covers. spread: alter each cover as little as possible (default). tight: pack multiple secrets per cover. quality: preserve visual quality above all else.
- `password` (string, required): Encryption password. Required for hide and reveal. At least 8 characters with mixed case, a digit, and a symbol.
- `scale_secret_to_fit` (boolean): Hide only. Auto-reduce secret size when it is too large to fit in its cover — images are resized, videos are compressed further. Set false to fail instead. Default: true.
- `secret_video_codec` (string): Hide only, video secrets. Codec for compressing secret videos. h265 gives ~40% smaller payloads. Default: h265.
- `secret_video_crf` (integer): Hide only, video secrets. Compression quality for secret videos (lower = better quality, larger payload). Default: 28.
- `strip_cover_metadata` (boolean): Hide only. Remove EXIF, GPS, and all embedded metadata from the stego output cover. Default: false.
- `strip_secret_metadata` (boolean): Hide only. Remove EXIF, GPS, and embedded metadata from secret files before hiding. Reduces payload size. Default: false.
- `upload_uid` (string, required): The upload_uid returned by vaultify_session_create
- `vault_profile_id` (integer): Pro accounts only, hide jobs only. ID of a Vault Profile to use as an additional key factor. Vault profiles are created and managed at /vault in the web UI. Returns error code -32002 on free accounts.
- `video_output_format` (string): Hide only, video covers. Lossless codec and container for stego video output. Default: ffv1_mkv.

### `vaultify_job_status` (~59 tokens)

Returns the current status and progress of a hide/reveal processing job. Poll until status is "completed" or "failed". Requires X-Api-Key header.

Input parameters:

- `upload_uid` (string, required): The upload_uid returned by vaultify_session_create

### `vaultify_job_results` (~68 tokens)

Returns download info for all result files once a hide/reveal job is complete. result_files is empty while the job is still processing — poll vaultify_job_status first. Requires X-Api-Key header.

Input parameters:

- `upload_uid` (string, required): The upload_uid returned by vaultify_session_create

### `snapwonders_analyse_session_create` (~115 tokens)

Creates an upload session for forensic media analysis. Returns the upload_uid and upload instructions. Upload each file with a single POST /api/upload carrying the file as the request body; its response reports ready_for_job_start, so no separate verification call is needed before snapwonders_analyse_job_start. Direct upload accepts files up to max_upload_bytes (returned in this response, currently 95 MB); anything larger must use the resumable TUS endpoint at /api/tus. Requires X-Api-Key header.

### `snapwonders_analyse_session_files` (~67 tokens)

Lists all files uploaded to an analyse session. Verify all files show status "completed" before calling snapwonders_analyse_job_start. Requires X-Api-Key header.

Input parameters:

- `upload_uid` (string, required): The upload_uid returned by snapwonders_analyse_session_create

### `snapwonders_analyse_job_start` (~218 tokens)

Submits analysis options and queues a forensic analysis job. Returns upload_uid and job_uid. The call is idempotent. Requires X-Api-Key header.

Input parameters:

- `expiry` (string): How long the analysis result remains accessible after the job completes. Default: 1d. Free-tier keys are silently clamped to upload.free_max_expiry (default 1d); Pro accounts get the requested value.
- `face_detection` (boolean): Enable YuNet face detection. Default: true.
- `face_sensitivity` (string): standard: confidence threshold 0.5 (fewer false positives). thorough: threshold 0.2 (catches more faces). Default: standard.
- `forensic_depth` (string): standard: core forensic checks. deep: extended checks (reserved, currently identical to standard). Default: standard.
- `text_detection` (boolean): Enable OCR / text region detection. Default: true.
- `upload_uid` (string, required): The upload_uid returned by snapwonders_analyse_session_create

### `snapwonders_analyse_job_status` (~67 tokens)

Returns the current status and per-item progress of an analysis job. Poll until status is "completed", "partial", or "failed". Requires X-Api-Key header.

Input parameters:

- `upload_uid` (string, required): The upload_uid returned by snapwonders_analyse_session_create

### `snapwonders_analyse_job_results` (~116 tokens)

Returns per-item forensic analysis results including overall_grade (A–F; the Authenticity grade — edited, generated or re-encoded), exposure_grade (A–F; what the file gives away — privacy and hidden data), face_count, text_region_count, and watermark_flagged. Returns job_uid which can be passed to snapwonders_analyse_result for the clean summary. Requires X-Api-Key header.

Input parameters:

- `upload_uid` (string, required): The upload_uid returned by snapwonders_analyse_session_create

### `snapwonders_analyse_result` (~104 tokens)

Returns clean forensic result JSON by job_uid — file names, grades (A–F), detection counts, and analysis asset IDs (face overlays, ELA maps, etc.). The job_uid is returned by snapwonders_analyse_job_start and snapwonders_analyse_job_results. Requires X-Api-Key header.

Input parameters:

- `job_uid` (string, required): The job_uid returned by snapwonders_analyse_job_start or snapwonders_analyse_job_results

### `snapwonders_convert_session_create` (~110 tokens)

Creates an upload session for media conversion (images and videos). Returns the upload_uid and upload instructions. Upload each file with a single POST /api/upload carrying the file as the request body; its response reports ready_for_job_start, then call snapwonders_convert_job_start. Direct upload accepts files up to max_upload_bytes (returned in this response, currently 95 MB); anything larger must use the resumable TUS endpoint at /api/tus. Requires X-Api-Key header.

### `snapwonders_convert_session_files` (~64 tokens)

Lists all files uploaded to a convert session. Verify all files show status "completed" before calling snapwonders_convert_job_start. Requires X-Api-Key header.

Input parameters:

- `upload_uid` (string, required): The upload_uid returned by snapwonders_convert_session_create

### `snapwonders_convert_job_start` (~394 tokens)

Submits conversion options and queues a media conversion job. Images and videos in the session are converted to the specified format. The call is idempotent. Requires X-Api-Key header.

Input parameters:

- `expiry` (string): How long the converted files remain accessible after the job completes. Default: 1d. Free-tier keys are silently clamped to upload.free_max_expiry (default 1d); Pro accounts get the requested value.
- `image_format` (string): Output format for image files. Default: jpeg.
- `image_quality` (integer): JPEG/WebP output quality 1–100. Default: 85.
- `image_resize_height` (integer): Resize images to fit within this bounding-box height in pixels. Longest-edge fit, aspect preserved, no upscaling.
- `image_resize_width` (integer): Resize images to fit within this bounding-box width in pixels. Longest-edge fit, aspect preserved, no upscaling.
- `pdf_dpi` (integer): PDF only. Render resolution in DPI. Default: 150.
- `pdf_page_from` (integer): PDF only. First page to render, 1-based. Default: 1.
- `pdf_page_to` (integer): PDF only. Last page to render, 1-based. 0 means all pages. Default: 0.
- `strip_metadata` (boolean): Strip EXIF/GPS/encoder metadata from output files. Default: false.
- `upload_uid` (string, required): The upload_uid returned by snapwonders_convert_session_create
- `video_crf` (integer): Video CRF value 0–51 (lower = better quality). Default: 23.
- `video_format` (string): Output format for video files. Default: mp4h264.
- `video_max_dimension` (integer): Cap video resolution to this height in pixels. Omit for original resolution.

### `snapwonders_convert_job_status` (~65 tokens)

Returns the current status and per-item progress of a conversion job. Poll until status is "completed", "partial", or "failed". Requires X-Api-Key header.

Input parameters:

- `upload_uid` (string, required): The upload_uid returned by snapwonders_convert_session_create

### `snapwonders_convert_job_results` (~78 tokens)

Returns per-item conversion results with asset_id for each output file. Use the asset_id with GET /api/convert/download/{assetId} and the same X-Api-Key to download each file. Requires X-Api-Key header.

Input parameters:

- `upload_uid` (string, required): The upload_uid returned by snapwonders_convert_session_create

## Diagnostics

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

## Score history

- 2026-10-23: 68
- 2026-10-22: 67
- 2026-10-21: 67
- 2026-10-20: 67
- 2026-10-19: 66
- 2026-10-18: 66
- 2026-10-17: 65
- 2026-10-16: 64
- 2026-10-15: 64

## Common questions

### What is the snapWONDERS Vaultify MCP server?

snapWONDERS Vaultify is an MCP server listed in the public MCP registry as com.snapwonders/mcp. Hosted snapWONDERS MCP: hide files in images, reveal hidden content, analyse media, convert formats. This page covers its hosted endpoint (https://snapwonders.com/mcp).

### Is the snapWONDERS Vaultify MCP server safe to use?

snapWONDERS Vaultify scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the snapWONDERS Vaultify MCP server expose?

snapWONDERS Vaultify exposes 19 tools: status, vaultify_get_started, snapwonders_get_started, vaultify_session_create, vaultify_session_files, and 14 more. Their descriptions and schemas cost roughly 2,445 tokens of context every time the server is loaded.

### Does the snapWONDERS Vaultify MCP server require authentication?

No. We connected to snapWONDERS Vaultify without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the snapWONDERS Vaultify MCP server still maintained?

snapWONDERS Vaultify is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://snapwonders.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-snapwonders-mcp/snapwonders.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-snapwonders-mcp/snapwonders.json
- HTML version of this page: https://verifymcp.io/servers/com-snapwonders-mcp/snapwonders