# AirGallery (remote · wgbduttegyrwiukjhubh.supabase.co)

AI photo tools and 18 image models (GPT Image 2.6, Nano Banana, FLUX 3, more) over MCP. Pay per use.

- Trust score: 67/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `wgbduttegyrwiukjhubh.supabase.co`: 67/100 (this document), [markdown](https://verifymcp.io/servers/com-airgallery-airgallery/functions-v1-mcp-server.md), [page](https://verifymcp.io/servers/com-airgallery-airgallery/functions-v1-mcp-server)

## Channel facts

- Endpoint: `https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.2`

## 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 2026-11-21.

- **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 60 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**: 75/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 5213 tokens (~86/item across 60 items; 60 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**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 98% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 7 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_artwork" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 60 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the AirGallery MCP server?

AirGallery is a hosted endpoint at https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server, 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-airgallery-airgallery 'https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server'
```

### Cursor

```json
{
  "mcpServers": {
    "com-airgallery-airgallery": {
      "url": "https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-airgallery-airgallery": {
      "type": "http",
      "url": "https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-airgallery-airgallery]
url = "https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-airgallery-airgallery": {
      "type": "remote",
      "url": "https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-airgallery-airgallery --url 'https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-airgallery-airgallery:
    url: "https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server"
```

### Netclaw

```json
{
  "McpServers": {
    "com-airgallery-airgallery": {
      "Transport": "http",
      "Url": "https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-airgallery-airgallery -t streamable-http -u 'https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server'
```

### Other

```json
{
  "mcpServers": {
    "com-airgallery-airgallery": {
      "type": "http",
      "url": "https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server"
    }
  }
}
```

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.

### 2026-11-21 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-20 (score 66, 0)

- [functional] Server version: 1.4.0 → 1.5.0
- [functional] New tool “studio_update_objects”

### 2026-11-19 (score 66, +1)

- [security] Tool “create_image” rewrote its description, which is the text the model reads
- [security] Tool “get_credit_costs” rewrote its description, which is the text the model reads
- [security] Tool “remove_background” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 3496 → 5073
- [functional] Server version: 1.2.2 → 1.4.0
- [functional] New tool “buy_credits”
- [functional] New tool “get_portfolio”
- [functional] New tool “get_public_portfolio”
- [functional] New tool “list_my_portfolios”
- [functional] New tool “publish_portfolio”
- [functional] New tool “search_artworks”
- [functional] New tool “studio_add_elements”
- [functional] New tool “studio_add_font”
- [functional] New tool “studio_add_frames”
- [functional] New tool “studio_create_document”
- [functional] New tool “studio_delete_objects”
- [functional] New tool “studio_generate_layout”
- [functional] New tool “studio_get_document”
- [functional] New tool “studio_list_documents”
- [functional] New tool “update_artwork”
- [cosmetic] “remove_background” added an optional parameter “bg_color”
- [cosmetic] “upscale_image” added an optional parameter “outputHeight”
- [cosmetic] “upscale_image” added an optional parameter “outputWidth”
- [cosmetic] “create_image” reworded the description of “model”

### 2026-11-17 (score 65, +1)

- [security] Tool “create_image” rewrote its description, which is the text the model reads
- [security] Tool “get_pricing_tiers” rewrote its description, which is the text the model reads
- [functional] Server version: 1.2.1 → 1.2.2

### 2026-11-16 (score 64, +1)

- [functional] MCP protocol version: 2025-03-26 → 2025-06-18
- [functional] Server version: 1.2.0 → 1.2.1

### 2026-11-15 (score 63, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-14 (score 63)

First indexed and scored.

## MCP tools (60)

### `list_public_artworks` (~75 tokens)

Browse the public AirGallery discover feed. Returns artworks with image URLs, prompts, tags, and creator info. Supports pagination.

Input parameters:

- `limit` (number): Max results (default 20, max 100)
- `offset` (number): Pagination offset (default 0)
- `tag` (string): Filter by tag

### `get_artwork` (~37 tokens)

Get details of a specific artwork by ID including image URL, prompt, tags, and metadata.

Input parameters:

- `id` (string, required): Artwork UUID

### `list_my_artworks` (~45 tokens)

List the authenticated user's saved artworks (private gallery). Requires auth.

Input parameters:

- `limit` (number): Max results (default 20)
- `offset` (number): Pagination offset

### `save_artwork` (~163 tokens)

Save an artwork to the authenticated user's gallery. A data:image URI (PNG, JPEG, WebP or GIF) is uploaded to AirGallery storage and the artwork stores the resulting public URL; http(s) URLs are stored as given. Requires auth + 'write' scope.

Input parameters:

- `image_url` (string, required): http(s) image URL, or a data:image/…;base64 URI up to ~10 MB (e.g. a create_image result)
- `is_public` (boolean): Whether to make the artwork public (default false)
- `model` (string): AI model used
- `preset` (string): Preset/style used
- `prompt` (string): Prompt used to generate the image
- `tags` (array): Tags for the artwork

### `delete_artwork` (~37 tokens)

Delete an artwork from the authenticated user's gallery. Requires auth + 'write' scope.

Input parameters:

- `id` (string, required): Artwork UUID to delete

### `search_artworks` (~74 tokens)

Search the public AirGallery feed by keyword (matches prompts and tags). Returns artworks with image URLs, prompts and tags.

Input parameters:

- `limit` (number): Max results (default 20, max 100)
- `query` (string, required): Keyword or phrase, e.g. 'cyberpunk city' or 'watercolor'

### `update_artwork` (~93 tokens)

Update one of the authenticated user's artworks: make it public or private, replace its tags, or edit its prompt. Requires auth + 'write' scope.

Input parameters:

- `id` (string, required): Artwork UUID
- `is_public` (boolean): Show it in the public gallery
- `prompt` (string): New prompt / description
- `tags` (array): New tags (replaces the existing ones, max 20)

### `get_credit_balance` (~20 tokens)

Get the authenticated user's current credit balance. Requires auth.

### `get_credit_costs` (~54 tokens)

Get the credit cost of each AI tool, keyed by MCP tool name (create_image:<model> for each image model). generate_tags is free the first time for your own untagged artwork. No auth required.

### `get_pricing_tiers` (~23 tokens)

Get available credit purchase tiers and prices. No auth required.

### `buy_credits` (~102 tokens)

Start a credit purchase: returns a checkout URL for the user to open and pay in their browser (get tier ids from get_pricing_tiers). Credits never expire. Requires auth.

Input parameters:

- `cancel_url` (string): Where to send the user if they cancel
- `pricing_tier_id` (string, required): Tier id from get_pricing_tiers
- `success_url` (string): Where to send the user after paying (default airgallery.com/credits)

### `remove_background` (~95 tokens)

Remove the background from an image, leaving the subject on transparency (or on a solid colour with bg_color). Returns { processedImage }. Cost: 1 credit.

Input parameters:

- `bg_color` (string): Optional solid background instead of transparency: hex (#ffffff / ffffff) or a colour name
- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL

### `enhance_image` (~75 tokens)

Enhance image quality: general clean-up, sharpen, denoise or fix lighting. Returns { image }. Cost: 1 credit.

Input parameters:

- `enhanceType` (string): Kind of enhancement (default general)
- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL

### `upscale_image` (~234 tokens)

Upscale an image 1–6x with Topaz Gigapixel AI. Returns { image }. Cost: 3 credits.

Input parameters:

- `denoise` (number): Denoise amount 0–1 (default 0)
- `faceEnhancement` (boolean): Enhance faces (default false)
- `faceEnhancementStrength` (number): Face enhancement strength 0–1 (default 0.5)
- `fixCompression` (number): Compression artifact removal 0–1 (default 0)
- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL
- `model` (string): Topaz model (default Standard V2)
- `outputHeight` (number): Exact output height in pixels (used when outputWidth isn't set)
- `outputWidth` (number): Exact output width in pixels (instead of scale; height follows the aspect ratio)
- `scale` (number): Upscale factor from 1 to 6 (default 2)
- `sharpen` (number): Sharpen amount 0–1 (default 0)

### `text_to_image` (~92 tokens)

Generate an image from a text prompt with a style and aspect ratio. Returns { generatedImage }. Cost: 3 credits. For a choice of image models use create_image.

Input parameters:

- `aspectRatio` (string): Aspect ratio (default 1:1)
- `prompt` (string, required): Text description of the image (max 2000 chars)
- `style` (string): Style (default photorealistic)

### `ai_replace` (~99 tokens)

Replace a marked area of an image with something described in words. Returns { processedImage }. Cost: 3 credits.

Input parameters:

- `image` (string, required): The image with the area to change painted over in semi-transparent red brush strokes (the AirGallery app sends rgba(255, 80, 80, 0.6)), as a base64 data URI or HTTPS URL
- `replacePrompt` (string, required): What should appear in the marked area

### `ai_expand` (~87 tokens)

Expand (outpaint) an image beyond its borders. Returns { processedImage }. Cost: 3 credits.

Input parameters:

- `context` (string): Optional description of what to add in the new area
- `direction` (string): Where to extend (default all)
- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL

### `object_remover` (~108 tokens)

Erase marked objects from an image and fill the space naturally. Returns { processedImage }. Cost: 2 credits.

Input parameters:

- `image` (string, required): The image with the area to change painted over in semi-transparent red brush strokes (the AirGallery app sends rgba(255, 80, 80, 0.6)), as a base64 data URI or HTTPS URL
- `maskDescription` (string): Optional: what to remove, e.g. 'the person on the left'

### `colorize_image` (~66 tokens)

Colorize a black and white photograph. Returns { image }. Cost: 2 credits.

Input parameters:

- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL
- `style` (string): Color style (default natural)

### `cartoonize` (~65 tokens)

Turn a photo into a cartoon. Returns { processedImage }. Cost: 2 credits.

Input parameters:

- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL
- `style` (string): Cartoon style (default cartoon)

### `style_transfer` (~93 tokens)

Repaint a content image in the style of a second, style reference image. Returns { processedImage }. Cost: 2 credits.

Input parameters:

- `contentImage` (string, required): The photo to restyle: base64 data URI or HTTPS URL
- `strength` (string): Style strength (default medium)
- `styleImage` (string, required): The style reference (e.g. a painting): base64 data URI or HTTPS URL

### `relight_image` (~67 tokens)

Change the lighting of an image. Returns { processedImage }. Cost: 2 credits.

Input parameters:

- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL
- `lighting` (string): Lighting preset (default golden-hour)

### `dslr_transform` (~61 tokens)

Make a phone photo look like it was taken with a DSLR camera. Returns { image }. Cost: 2 credits.

Input parameters:

- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL

### `photo_repair` (~73 tokens)

Fix blur, noise, low resolution or general damage in a photo. Returns { processedImage }. Cost: 2 credits.

Input parameters:

- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL
- `type` (string): Repair type (default restore)

### `old_photo_restore` (~80 tokens)

Restore an old photograph: scratches, fading, stains, creases. Returns { processedImage }. Cost: 3 credits.

Input parameters:

- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL
- `options` (object): Restoration steps to apply (the app turns all of them on)

### `ai_filters` (~66 tokens)

Apply an artistic AI filter to an image. Returns { image }. Cost: 1 credit.

Input parameters:

- `filter` (string, required): Filter (default oilPainting)
- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL

### `retro_transform` (~68 tokens)

Apply a retro look to an image. Returns { processedImage }. Cost: 1 credit.

Input parameters:

- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL
- `style` (string): Retro style (default 70s)

### `polaroid_transform` (~58 tokens)

Turn an image into a Polaroid instant print. Returns { image }. Cost: 1 credit.

Input parameters:

- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL

### `headshot_generator` (~60 tokens)

Generate a professional headshot from a selfie. Returns { processedImage }. Cost: 3 credits.

Input parameters:

- `image` (string, required): Clear face photo: base64 data URI or HTTPS URL
- `style` (string): Headshot style (default linkedin)

### `portrait_retouch` (~76 tokens)

Retouch a portrait naturally. Returns { processedImage }. Cost: 2 credits.

Input parameters:

- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL
- `options` (object): Enhancements to apply (none set = general skin, eye and lighting touch-up)

### `avatar_generator` (~69 tokens)

Generate a stylized avatar from a face photo. Returns { processedImage }. Cost: 3 credits.

Input parameters:

- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL
- `style` (string): Avatar style (default pixar)

### `meme_generator` (~88 tokens)

Add classic top/bottom meme captions to an image. At least one caption is required. Returns { processedImage }. Cost: 1 credit.

Input parameters:

- `bottomText` (string): Caption at the bottom
- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL
- `topText` (string): Caption at the top

### `product_studio` (~83 tokens)

Turn a product photo into a styled e-commerce shot. Returns { processedImage }. Cost: 3 credits.

Input parameters:

- `background` (string): Scene (default white_studio)
- `customPrompt` (string): Optional custom scene description
- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL

### `logo_mockup` (~64 tokens)

Place a logo on a realistic merchandise or signage mockup. Returns { processedImage }. Cost: 2 credits.

Input parameters:

- `image` (string, required): Logo image: base64 data URI or HTTPS URL
- `mockupType` (string): Mockup (default tshirt)

### `poster_generator` (~57 tokens)

Design a poster from a description. Returns { generatedImage }. Cost: 3 credits.

Input parameters:

- `prompt` (string, required): What the poster is for: title, event details, mood
- `style` (string): Design style (default modern)

### `aspect_ratio_change` (~70 tokens)

Change an image's aspect ratio, filling new space with AI. Returns { processedImage }. Cost: 2 credits.

Input parameters:

- `aspectRatio` (string, required): Target ratio
- `image` (string, required): Image as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL

### `studio_generate_layout` (~143 tokens)

Design a layout from a brief: returns { layout: { name, background, layers[] } } with rect, ellipse, text and image layers positioned in pixels on a width×height artboard. Place it in a Design Studio file with studio_create_document / studio_add_frames / studio_add_elements. Cost: 1 credit.

Input parameters:

- `height` (number): Artboard height in pixels (optional)
- `prompt` (string, required): What to design, e.g. 'Instagram post announcing a summer sale, bold and warm' (max 2000 chars)
- `width` (number): Artboard width in pixels (optional; chosen to suit the brief when omitted)

### `generate_tags` (~72 tokens)

Generate 5–8 descriptive tags for an image. Returns { tags }. Cost: 1 credit; free the first time for one of your own saved artworks that has no tags yet.

Input parameters:

- `image_url` (string, required): Image URL (e.g. a saved artwork's image_url) or base64 data URI

### `create_image` (~862 tokens)

Create or transform an image using AirGallery's core multi-modal image pipeline (powers the Create page). Accepts up to 5 reference images plus a custom prompt and/or style preset, and supports multiple image models. Every model accepts reference images except recraft-v4.1, recraft-v4.1-flash (text only; images are rejected and refunded). Returns { image }. Cost depends on the model, in credits: nano-banana-2 3, nano-banana-pro 6, nano-banana-2-lite 2, nano-banana 3, gpt-image-2.6-flare 8, gpt-image-2.6-sunburst 8, gpt-image-2.5-flare 8, gpt-image-2.5-sunburst 8, gpt-image 8, gpt-image-mini 3, flux-3 3, flux-3-klein 1, mai-image-2.6 3, grok-imagine-2 4, seedream-5-pro 2, muse-image 1, minimax-h3 2, recraft-v4.1 2, mai-image-2.7 3, mai-image-2.7-flash 1, seedream-5.5 2, recraft-v4.1-flash 1. Requires 'ai' scope.

Input parameters:

- `customPrompt` (string): Free-form description of what to create (max 2000 chars). Required when no images are given.
- `images` (array): Optional: 0–5 reference images, each as a base64 data URI or HTTPS image URL. Omit for pure text-to-image (customPrompt is then required).
- `model` (string): Image model: 'nano-banana-2' (Gemini 3.1 Flash Image, default), 'nano-banana-pro' (Gemini 3 Pro Image), 'nano-banana-2-lite' (Gemini 3.1 Flash-Lite Image, fast and cheap), 'nano-banana' (Gemini 2.5 F…
- `plugins` (object): Optional effects (the Create page's Plugins & Effects).
- `preset` (string): Style preset applied to the images and/or prompt (default none).

### `get_my_profile` (~24 tokens)

Get the authenticated user's profile (username, bio, avatar). Requires auth.

### `update_my_profile` (~70 tokens)

Update the authenticated user's profile (username, bio, avatar_url). Requires auth + 'write' scope.

Input parameters:

- `avatar_url` (string): URL to avatar image
- `bio` (string): Bio text (max 300 chars)
- `username` (string): Display name (max 30 chars)

### `get_user_profile` (~28 tokens)

Get a public user profile by user ID.

Input parameters:

- `user_id` (string, required): User UUID

### `follow_user` (~33 tokens)

Follow another user. Requires auth + 'write' scope.

Input parameters:

- `user_id` (string, required): UUID of user to follow

### `unfollow_user` (~36 tokens)

Unfollow a user. Requires auth + 'write' scope.

Input parameters:

- `user_id` (string, required): UUID of user to unfollow

### `like_artwork` (~34 tokens)

Like a public artwork. Requires auth + 'write' scope.

Input parameters:

- `artwork_id` (string, required): Artwork UUID to like

### `unlike_artwork` (~36 tokens)

Remove a like from an artwork. Requires auth + 'write' scope.

Input parameters:

- `artwork_id` (string, required): Artwork UUID to unlike

### `list_my_white_label_galleries` (~23 tokens)

List the authenticated user's white-label galleries. Requires auth.

### `get_white_label_gallery` (~28 tokens)

Get a public white-label gallery by slug.

Input parameters:

- `slug` (string, required): Gallery slug

### `studio_list_documents` (~41 tokens)

List the authenticated user's Design Studio files (newest first). Requires auth.

Input parameters:

- `limit` (number): Max results (default 20, max 100)

### `studio_get_document` (~66 tokens)

Outline of a Design Studio file: its frames (id, name, position, size) with the elements in each (id, type, position relative to the frame, text and font), and its uploaded fonts. Requires auth.

Input parameters:

- `document_id` (string, required): Studio document UUID

### `studio_create_document` (~116 tokens)

Create a Design Studio file, optionally with frames and their elements in one call. Frames are laid out left to right. For print, size frames in inches (width_in/height_in at 300 DPI); the Studio's print export turns them into a PDF at that trim size with bleed and crop marks. Returns the file's id, its editor URL and the ids of what was created. Requires auth (write).

Input parameters:

- `frames` (array): Frames to create
- `name` (string): File name (default Untitled)

### `studio_add_frames` (~88 tokens)

Add frames (each optionally with elements) to a Design Studio file, to the right of the existing ones. Changes are saved to the cloud file; an editor tab that already has the file open must be reloaded to see them (and would overwrite them if it saves first). Requires auth (write).

Input parameters:

- `document_id` (string, required): Studio document UUID
- `frames` (array, required)

### `studio_add_elements` (~136 tokens)

Add text, rectangles, ellipses or SVG paths to a frame of a Design Studio file. Positions are px from the frame's top-left. Text wraps inside its width; use align center with x 0 and the frame's width to center it. Changes are saved to the cloud file; an editor tab that already has the file open must be reloaded to see them (and would overwrite them if it saves first). Requires auth (write).

Input parameters:

- `document_id` (string, required): Studio document UUID
- `elements` (array, required)
- `frame_id` (string, required): Frame id from studio_get_document / studio_create_document

### `studio_delete_objects` (~90 tokens)

Delete frames or elements from a Design Studio file by id (deleting a frame deletes its contents). Changes are saved to the cloud file; an editor tab that already has the file open must be reloaded to see them (and would overwrite them if it saves first). Requires auth (write).

Input parameters:

- `document_id` (string, required): Studio document UUID
- `ids` (array, required): Frame or element ids

### `studio_update_objects` (~140 tokens)

Change frames or elements of a Design Studio file in place: move, resize, restyle or retext them without deleting and re-adding. Each update has the object's id plus only the fields to change, with the same names as studio_add_elements (x/y relative to the frame). Frames take name, width, height and background. Changes are saved to the cloud file; an editor tab that already has the file open must be reloaded to see them (and would overwrite them if it saves first). Requires auth (write).

Input parameters:

- `document_id` (string, required): Studio document UUID
- `updates` (array, required): One entry per object to change

### `studio_add_font` (~185 tokens)

Add a font file (TTF, OTF, WOFF or WOFF2) to a Design Studio file so text can use it by family name — for fonts that aren't on Google Fonts. Give either a public https URL or the file as base64. TTF, OTF and WOFF embed in PDF exports. Replaces a font of the same family. Changes are saved to the cloud file; an editor tab that already has the file open must be reloaded to see them (and would overwrite them if it saves first). Requires auth (write).

Input parameters:

- `data_base64` (string): The font file, base64-encoded
- `document_id` (string, required): Studio document UUID
- `family` (string, required): Family name text elements will use, e.g. 'Helyna'
- `url` (string): https URL of the font file

### `list_my_portfolios` (~27 tokens)

List the authenticated user's portfolio sites with their public URLs and published state. Requires auth.

### `get_portfolio` (~46 tokens)

Get one of the authenticated user's portfolios with its theme and pages (each page's content blocks). Requires auth.

Input parameters:

- `id` (string, required): Portfolio UUID (from list_my_portfolios)

### `publish_portfolio` (~65 tokens)

Publish or unpublish one of the authenticated user's portfolios. Published portfolios are public at airgallery.com/p/<slug>. Requires auth + 'write' scope.

Input parameters:

- `id` (string, required): Portfolio UUID
- `publish` (boolean, required): true to publish, false to take it offline

### `get_public_portfolio` (~47 tokens)

Get a published, non-password-protected portfolio by its slug (airgallery.com/p/<slug>) with its pages. No auth required.

Input parameters:

- `slug` (string, required): Portfolio slug

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-airgallery-airgallery/functions-v1-mcp-server#diagnostics

## Score history

- 2026-11-21: 67
- 2026-11-20: 66
- 2026-11-19: 66
- 2026-11-18: 65
- 2026-11-17: 65
- 2026-11-16: 64
- 2026-11-15: 63
- 2026-11-14: 63

## Common questions

### What is the AirGallery MCP server?

AirGallery is an MCP server listed in the public MCP registry as com.airgallery/airgallery. AI photo tools and 18 image models (GPT Image 2.6, Nano Banana, FLUX 3, more) over MCP. Pay per use. This page covers its hosted endpoint (https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server).

### Is the AirGallery MCP server safe to use?

AirGallery scores 67 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 AirGallery MCP server expose?

AirGallery exposes 60 tools: list_public_artworks, get_artwork, list_my_artworks, save_artwork, delete_artwork, and 55 more. Their descriptions and schemas cost roughly 5,213 tokens of context every time the server is loaded.

### Does the AirGallery MCP server require authentication?

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

### Is the AirGallery MCP server still maintained?

AirGallery is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the AirGallery MCP server?

VerifyMCP ran 12 checks on AirGallery, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about AirGallery: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server
- Authorisation metadata: https://wgbduttegyrwiukjhubh.supabase.co/.well-known/oauth-protected-resource/functions/v1/mcp-server
- Website: https://airgallery.com/api
- Changelog RSS feed: https://verifymcp.io/servers/com-airgallery-airgallery/functions-v1-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-airgallery-airgallery/functions-v1-mcp-server/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-airgallery-airgallery/functions-v1-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/com-airgallery-airgallery/functions-v1-mcp-server
