Model Context Protocol · Pixazo MCP servers live

Connect any AI agent to Pixazo

Image, video, audio, music, 3D, and upscale — available as live MCP servers for Claude, Cursor, Codex, OpenAI Atlas, and any MCP-compatible client. Sign in with your Pixazo account once; usage flows through your existing credits.

Get the Pixazo MCP Or pick a model

Recommended · The Pixazo MCP

One MCP. Every model.

A single connector that gives your agent access to image, video, audio, music, 3D, and upscale capabilities — routing to the best Pixazo model for each task with a smart default (or whatever model you specify). Twelve high-level tools instead of dozens of per-model ones.

https://gateway.pixazo.ai/pixazo/mcp

claude mcp add pixazo https://gateway.pixazo.ai/pixazo/mcp

What's inside

Video→seedance, happy-horse
Image→gpt-image, nano-banana
Music→minimax-music
Speech→vibevoice, elevenlabs
3D→meshy-6
Upscale→topaz

Quickstart

One URL. Any agent.

The Pixazo MCP exposes 12 high-level intent tools through a single OAuth-protected endpoint. Pick your client and paste the snippet — the agent handles routing.

# Add the Pixazo MCP to Claude Code
claude mcp add pixazo https://gateway.pixazo.ai/pixazo/mcp

# Then ask in any chat:
# > generate a sunset over a misty mountain range, then animate it slowly
# (the agent picks the right Pixazo model for each step)

// Add to Cursor's mcp.json (Settings → MCP → Add)
{
  "mcpServers": {
    "pixazo": {
      "url": "https://gateway.pixazo.ai/pixazo/mcp"
    }
  }
}

# Add to ~/.codex/config.toml

[mcp.servers.pixazo]
url = "https://gateway.pixazo.ai/pixazo/mcp"

# Discover the OAuth metadata for the Pixazo MCP
curl 'https://gateway.pixazo.ai/pixazo-image-oauth/.well-known/oauth-protected-resource?resource=https%3A%2F%2Fgateway.pixazo.ai%2Fpixazo%2Fmcp'

Or target a specific model

Per-model MCPs

Power-user mode — bypass the umbrella and connect directly to the model you want. Same OAuth, same per-user attribution.

Image

Video

Hailuo

MiniMax · v2.3

Image → VideoText → Video

gateway.pixazo.ai/hailuo-mcp/mcp

Kling

Kuaishou · v2.6

Image → ImageImage → VideoText → Image

gateway.pixazo.ai/kling-mcp/mcp

Luma Dream Machine

Luma AI · v1.5

Image → VideoText → ImageText → Video

gateway.pixazo.ai/luma-mcp/mcp

P Video

Pruna AI · 1.0

Text → VideoImage → Video

gateway.pixazo.ai/p-video-mcp/mcp

Pika

Pika Labs · v2.2

Text → VideoImage → VideoReference → Video

gateway.pixazo.ai/pika-mcp/mcp

Runway

Runway · v4.5

Image → VideoText → VideoVideo → Video

gateway.pixazo.ai/runway-mcp/mcp

Seedance 2

BytePlus · 1-0-pro

Image → VideoText → VideoVideo → Video

gateway.pixazo.ai/seedance-mcp/mcp

Sora

OpenAI · sora-2-pro

Image → VideoText → Video

gateway.pixazo.ai/sora-mcp/mcp

Veo 3.1

Google · v3.1

Image → VideoText → VideoReference → Video

gateway.pixazo.ai/veo-mcp/mcp

Wan

Alibaba · v2.6

Image → ImageImage → VideoText → Image

gateway.pixazo.ai/wan-mcp/mcp

GenFlare

Baidu · 2.0

Image → Video

gateway.pixazo.ai/genflare-mcp/mcp

Grok Imagine Image

xAI · Pro Quality

Image → ImageText → Image

gateway.pixazo.ai/grok-imagine-image-mcp/mcp

Higgsfield

Higgsfield · v1

Image → VideoText → Image

gateway.pixazo.ai/higgsfield-mcp/mcp

LTX

Lightricks · v2.3

Image → VideoText → VideoAudio to Video

gateway.pixazo.ai/ltx-mcp/mcp

Lucy Edit

Decart · fast

Image → VideoText → VideoVideo → Video

gateway.pixazo.ai/lucy-edit-mcp/mcp

Mochi

Mochi · v1

Text → Video

gateway.pixazo.ai/mochi-mcp/mcp

OmniHuman

BytePlus · v1.5

AI LipsyncAudio to Video (Ref Image + Ref Audio to Video — Lipsync)

gateway.pixazo.ai/omnihuman-mcp/mcp

Pixverse

Pixverse · v6

Image → VideoText → VideoAI Lipsync

gateway.pixazo.ai/pixverse-mcp/mcp

Stable Diffusion

Stability AI · v3.5

Image → ImageImage → VideoText → Image

gateway.pixazo.ai/stable-diffusion-mcp/mcp

Vidu

Vidu · v1

Image → VideoText → VideoImage to Image (Image Background Remover)

gateway.pixazo.ai/vidu-mcp/mcp

Hunyuan Video

Tencent · v1

Text → VideoImage → VideoVideo → Video

gateway.pixazo.ai/hunyuan-video-mcp/mcp

Kandinsky

Kandinsky · v5-pro

Image → Video

gateway.pixazo.ai/kandinsky-mcp/mcp

Veed

Veed · v1.0

Image → VideoText → VideoVideo to Video (Video Background Remover)

gateway.pixazo.ai/veed-mcp/mcp

Happy Horse

Alibaba · v1.0

Text → VideoImage → VideoReference → Video

gateway.pixazo.ai/happy-horse-mcp/mcp

Audio · Music · TTS

ElevenLabs

ElevenLabs · v3

Text to SongText to MusicVoice Clone

gateway.pixazo.ai/elevenlabs-mcp/mcp

Gemini

Google · v3.1

Text → Speech

gateway.pixazo.ai/gemini-mcp/mcp

Lyria

Google · v2

Text to Music

gateway.pixazo.ai/lyria-mcp/mcp

VibeVoice

Microsoft · v1

Text → Speech

gateway.pixazo.ai/vibevoice-mcp/mcp

Ace Step

ACE Studio · v1.0

Text to SongText to Music

gateway.pixazo.ai/ace-step-mcp/mcp

Chatterbox

Resemble-ai · v1

Text → SpeechVoice Clone

gateway.pixazo.ai/chatterbox-mcp/mcp

Minimax

MiniMax · v2.3

Image → ImageText → ImageText to Song

gateway.pixazo.ai/minimax-mcp/mcp

Tracks

Pixazo · v1.0

Text to MusicText to SongFree

gateway.pixazo.ai/tracks-mcp/mcp

XTTS

Xtts · v2

Text → SpeechVoice Clone

gateway.pixazo.ai/xtts-mcp/mcp

Qwen TTS

Alibaba · v3

Text → Speech

gateway.pixazo.ai/qwen-tts-mcp/mcp

3D

Hunyuan

Tencent · v3.0

Image to Image ( 3D Models - Image to 3D)Image → ImageText → Image

gateway.pixazo.ai/hunyuan-mcp/mcp

Hyper3D

Hyper3D · v1

Image to Image (3D Models — Text & Image to 3D)

gateway.pixazo.ai/hyper3d-mcp/mcp

Trellis3d

Trellis · v2

Image to Image (3D Models — Image to 3D)

gateway.pixazo.ai/trellis3d-mcp/mcp

Tripo3D

Tripo · v2.5

Image to Image (3D Models — Image to 3D)

gateway.pixazo.ai/tripo3d-mcp/mcp

Meshy 6

Meshy · v6

Text → ImageImage → ImageImage to Image ( 3D Models - Image to 3D)

gateway.pixazo.ai/meshy-3d-mcp/mcp

Virtual Try-On

Fashn Virtual Try On

Fashn · v3

Image to Image (Virtual Try On)

gateway.pixazo.ai/fashn-vton-mcp/mcp

IDM VTON

IDM-VTON · v1

Image to Image (Virtual Try On)

gateway.pixazo.ai/idm-vton-mcp/mcp

Upscale & Restoration

P Image

Pruna AI · v1

Image → ImageImage to Image (Image Editing)Image to Image (Image Upscaler)

gateway.pixazo.ai/p-image-mcp/mcp

Crystal Upscaler

Clarityai · v1

Image to Image (Image Upscaler)

gateway.pixazo.ai/crystal-upscaler-mcp/mcp

Seed VR

Seed VR · v1

Image to Image (Image Upscaler)

gateway.pixazo.ai/seedvr-mcp/mcp

Topaz

Topaz · v1

Video to Video (Video Upscaler)

gateway.pixazo.ai/topaz-mcp/mcp

Codeformer

Sczhou · v1

Image Restoration

gateway.pixazo.ai/codeformer-mcp/mcp

GFPGAN API

TencentARC · v1

Image Restoration

gateway.pixazo.ai/gfpgan-mcp/mcp

What is MCP?

The plug-in standard for AI agents

Model Context Protocol is the open spec that lets any AI agent (Claude, Cursor, Codex, ChatGPT Atlas, OpenAI's SDK, custom clients) talk to external tools through a uniform OAuth-secured JSON-RPC interface.

One account, every model

Sign in once with your Pixazo account. The same credits and quota you use on the dashboard flow through every MCP call — no separate API keys, no duplicate billing.

OAuth via Cognito + APIM

Per-user authentication through AWS Cognito; Azure APIM injects your subscription key on each tool call so generations attribute correctly to your dashboard.

Built on the open standard

Every server speaks vanilla MCP — works in Claude, Cursor, Codex, OpenAI Atlas, and anything else that ships an MCP client. Add a server in 30 seconds.

FAQ

Pixazo MCP — common questions

Which AI models does the Pixazo MCP support?

Pixazo's MCP servers expose 70+ leading AI models:

Image: Seedream, Flux, GPT-Image, Nano Banana, Recraft, Ideogram, Studio Ghibli, Z-Image, Hidream, Auraflow, SDXL, Bria, Pixelforge, Qwen Image, Reve, Longcat, Ernie, GLM, Nucleus, FireRed Image Edit, Smart Resize.
Video: Seedance, Happy Horse, Sora, Veo, Runway, Kling, Pika, Luma, Hailuo, Wan, P-Video, Higgsfield, GenFlare, Lucy Edit, Grok Imagine, LTX, Mochi, Stable Diffusion, Vidu, Kandinsky, Hunyuan Video, Pixverse, Veed, OmniHuman.
Audio / TTS / Music: VibeVoice, ElevenLabs, MiniMax Music, Lyria, Gemini, Chatterbox, XTTS, Tracks, ACE Step, Qwen-TTS.
3D: Meshy 6, Hunyuan, Hyper3D, Tripo3D, Trellis3D.
Virtual Try-On: Fashn VTON, IDM-VTON.
Upscale & restoration: Topaz, P-Image, Crystal Upscaler, SeedVR, GFPGAN, CodeFormer.

Browse the full per-model directory below or use the curated Pixazo MCP umbrella to access them all through one connector.

Does Pixazo MCP work with Claude, Cursor, Codex, and OpenAI Atlas?

Yes. Every Pixazo MCP server speaks vanilla Model Context Protocol, so it works with any MCP-compatible client — Claude Code, Claude Desktop, Cursor, OpenAI Codex, ChatGPT Atlas, and OpenAI's MCP SDK. Setup is one line per client — see the Quickstart tabs.

Can I generate images through MCP?

Yes — Pixazo offers MCP servers for every leading image generation and editing model: GPT-Image, Nano Banana, Seedream 5.0 Lite, Flux 2, Recraft, Ideogram, Studio Ghibli, Z-Image, Hidream and more. Use the umbrella tool pixazoGenerateImage(prompt, model) for automatic routing, or connect directly to a per-model MCP like seedream-mcp or flux-mcp from the directory below.

What about video generation? Which video models does the MCP support?

The umbrella exposes Seedance and Happy Horse for video generation, image-to-video, reference-to-video, and video editing. The per-model directory adds Sora, Veo, Runway, Kling, Pika, Luma, Hailuo, Wan, P-Video, Mochi, LTX, Vidu, Kandinsky, Hunyuan Video, Pixverse, OmniHuman, and more. Each has its own MCP at gateway.pixazo.ai/<model>-mcp/mcp.

Does the Pixazo MCP support TTS, music, 3D, and upscaling?

Yes — full coverage across every category:

Speech / TTS: VibeVoice, ElevenLabs, XTTS, Chatterbox, Qwen-TTS
Music & songs: MiniMax Music, Lyria, ACE Step, Tracks
3D generation: Meshy 6, Hunyuan 3D, Tripo3D, Trellis3D, Hyper3D
Upscale & restoration: Topaz (image + video), P-Image, Crystal Upscaler, SeedVR, GFPGAN, CodeFormer

The Pixazo MCP umbrella exposes a high-level intent tool for each category; per-model MCPs give direct access if you need a specific one.

Is there an MCP for Seedance, Sora, Veo, Kling, Flux, Nano Banana, GPT-Image, ElevenLabs, or Topaz?

Yes — every model has its own dedicated MCP server. Quick reference:

gateway.pixazo.ai/seedance-mcp/mcp
gateway.pixazo.ai/sora-mcp/mcp
gateway.pixazo.ai/veo-mcp/mcp
gateway.pixazo.ai/kling-mcp/mcp
gateway.pixazo.ai/flux-mcp/mcp
gateway.pixazo.ai/runway-mcp/mcp
gateway.pixazo.ai/pika-mcp/mcp
gateway.pixazo.ai/nano-banana-mcp/mcp
gateway.pixazo.ai/gpt-image-mcp/mcp
gateway.pixazo.ai/seedream-mcp/mcp
gateway.pixazo.ai/happy-horse-mcp/mcp
gateway.pixazo.ai/elevenlabs-mcp/mcp
gateway.pixazo.ai/vibevoice-mcp/mcp
gateway.pixazo.ai/minimax-mcp/mcp (MiniMax Music)
gateway.pixazo.ai/topaz-mcp/mcp
gateway.pixazo.ai/meshy-3d-mcp/mcp

Or use the umbrella with model:"seedance", model:"flux", etc.

How do I add the Pixazo MCP to my AI agent?

For Claude Code: claude mcp add pixazo https://gateway.pixazo.ai/pixazo/mcp. For Cursor, OpenAI Codex, and ChatGPT Atlas, see the Quickstart tabsabove. OAuth via your Pixazo account on first connect; usage is billed to your dashboard credits — no separate API keys to manage.

How much does the Pixazo MCP cost? Is there a free tier?

Adding any Pixazo MCP server is free — you only pay for the generations themselves, billed at the same per-call rate as the Pixazo REST API. Many models include free trial credits. See the pricing page for current rates.

What's the difference between the Pixazo MCP umbrella and the per-model MCPs?

The Pixazo MCP umbrella at gateway.pixazo.ai/pixazo/mcp is one connector with 12 high-level intent tools (pixazoGenerateImage, pixazoGenerateVideo, pixazoTextToSpeech, etc.) that route to the best model for each task — with smart defaults and an optional model parameter. The per-model MCPs at gateway.pixazo.ai/<slug>-mcp/mcpgive direct access to a specific model's tools. Use the umbrella for general-purpose agents; use per-model when you want fine-grained control over a specific model.

Connect any AI agent to Pixazo

One MCP. Every model.

One URL. Any agent.

Per-model MCPs

FireRed Image Edit

Flux

GPT Image 2

Ideogram

Nano Banana 2

Recraft

Seedream

Smart Resize

Studio Ghibli

Auraflow

Bria

LongCat Image

Pixelforge

Qwen Image

Reve Image

SDXL

Z Image

Ernie Image

GLM Image

HiDream

Nucleus Image

Hailuo

Kling

Luma Dream Machine

P Video

Pika

Runway

Seedance 2

Sora

Veo 3.1

Wan

GenFlare

Grok Imagine Image

Higgsfield

LTX

Lucy Edit

Mochi

OmniHuman

Pixverse

Stable Diffusion

Vidu

Hunyuan Video

Kandinsky

Veed

Happy Horse

ElevenLabs

Gemini

Lyria

VibeVoice

Ace Step

Chatterbox

Minimax

Tracks

XTTS

Qwen TTS

Hunyuan

Hyper3D

Trellis3d

Tripo3D

Meshy 6

Fashn Virtual Try On

IDM VTON

P Image

Crystal Upscaler

Seed VR

Topaz

Codeformer

GFPGAN API

The plug-in standard for AI agents

One account, every model

OAuth via Cognito + APIM

Built on the open standard

Pixazo MCP — common questions

Which AI models does the Pixazo MCP support?

Does Pixazo MCP work with Claude, Cursor, Codex, and OpenAI Atlas?

Can I generate images through MCP?