Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

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.

+4 this week 67 Trust /100

Last scanned (13 hours ago)

Scores higher than 52% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Design and Media

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability75
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 5213 tokens (~86/item across 60 items; 60 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage99
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 98% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 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. See how to fix → Fail
  • An AI judge read all 60 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation 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.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +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.

  • 20 Nov 26 0
    • Server version: 1.4.0 → 1.5.0 functional
    • New tool “studio_update_objects” functional
  • 19 Nov 26 +1
    • 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 security
    • 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” functional
    • “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” cosmetic
  • 17 Nov 26 +1
    • 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 security
    • Server version: 1.2.1 → 1.2.2 functional
  • 16 Nov 26 +1
    • MCP protocol version: 2025-03-26 → 2025-06-18 functional
    • Server version: 1.2.0 → 1.2.1 functional
  • 15 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 14 Nov 26 63

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=supabase.co CN=WE1,O=Google Trust Services,C=US 24 Oct 2026 22 Jan 2027 ECDSA 256 ECDSA-SHA256 d2b50611cd88e9c50e4e2231f4d3f059
SANs: supabase.co, *.supabase.co
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of wgbduttegyrwiukjhubh.supabase.co. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
co. DS published 7786 8 Verified
supabase.co. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains; preload

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server Verified 200
http (plaintext) http://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server HTTPS enforced 301 https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server
MCP tools · 60 exposed · ~5,213 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
studio_get_document ~66

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.

NameTypeReqDescription
document_idstringyesStudio document UUID

No output schema declared.

No examples provided.

studio_list_documents ~41

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

NameTypeReqDescription
limitnumber–Max results (default 20, max 100)

No output schema declared.

No examples provided.

studio_update_objects ~140

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).

NameTypeReqDescription
document_idstringyesStudio document UUID
updatesarrayyesOne entry per object to change

No output schema declared.

No examples provided.

style_transfer ~93

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

NameTypeReqDescription
contentImagestringyesThe photo to restyle: base64 data URI or HTTPS URL
strengthstring–Style strength (default medium)
styleImagestringyesThe style reference (e.g. a painting): base64 data URI or HTTPS URL

No output schema declared.

No examples provided.

text_to_image ~92

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.

NameTypeReqDescription
aspectRatiostring–Aspect ratio (default 1:1)
promptstringyesText description of the image (max 2000 chars)
stylestring–Style (default photorealistic)

No output schema declared.

No examples provided.

unfollow_user ~36

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

NameTypeReqDescription
user_idstringyesUUID of user to unfollow

No output schema declared.

No examples provided.

unlike_artwork ~36

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

NameTypeReqDescription
artwork_idstringyesArtwork UUID to unlike

No output schema declared.

No examples provided.

update_artwork ~93

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

NameTypeReqDescription
idstringyesArtwork UUID
is_publicboolean–Show it in the public gallery
promptstring–New prompt / description
tagsarray–New tags (replaces the existing ones, max 20)

No output schema declared.

No examples provided.

update_my_profile ~70

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

NameTypeReqDescription
avatar_urlstring–URL to avatar image
biostring–Bio text (max 300 chars)
usernamestring–Display name (max 30 chars)

No output schema declared.

No examples provided.

upscale_image ~234

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

NameTypeReqDescription
denoisenumber–Denoise amount 0–1 (default 0)
faceEnhancementboolean–Enhance faces (default false)
faceEnhancementStrengthnumber–Face enhancement strength 0–1 (default 0.5)
fixCompressionnumber–Compression artifact removal 0–1 (default 0)
imagestringyesImage as a base64 data URI (data:image/png;base64,…) or an HTTPS image URL
modelstring–Topaz model (default Standard V2)
outputHeightnumber–Exact output height in pixels (used when outputWidth isn't set)
outputWidthnumber–Exact output width in pixels (instead of scale; height follows the aspect ratio)
scalenumber–Upscale factor from 1 to 6 (default 2)
sharpennumber–Sharpen amount 0–1 (default 0)

No output schema declared.

No examples provided.

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.

remote · wgbduttegyrwiukjhubh.supabase.co

# add to Claude Code
claude mcp add --transport http com-airgallery-airgallery 'https://wgbduttegyrwiukjhubh.supabase.co/functions/v1/mcp-server'
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.