SpecialX
Model Context Protocol · Beta

SpecialX inside your AI assistant.

Plug SpecialX into Claude, Cursor, ChatGPT, Windsurf, or any MCP-compatible client. Generate images and video, manage workspaces, and check task status straight from your assistant.

Connect to Claude

1

Open Claude settings

Launch the app or open claude.ai and go to

2

Add a custom connector

Name it SpecialX and paste the URL:

https://specialx.ai/api/mcp
3

Connect and sign in

Click Add → Connect, sign in with your SpecialX account — you're all set, now just ask Claude to generate an image.

What your assistant can do

Once connected, your client gets these 22 tools out of the box.

Generate

list_models

Lists available image and video models with their input schemas and credit costs.

generate_image

Submits an image generation job to a chosen model and workspace. Returns a task_id.

generate_video

Submits a video generation job (Veo, Kling, Sora, Grok, and more). Returns a task_id.

get_task

Polls the status of a generation task and returns the final media URLs when complete.

Media library

get_upload_url

Returns a presigned URL to upload your own image/video, plus the public URL to use it as a reference input.

list_media

Lists your uploaded media (or a workspace's generated outputs) to reference as inputs to generations.

Workspaces & workflows

list_workspaces

Returns the SpecialX workspaces the authenticated user belongs to.

create_workspace

Creates a new workspace (project container) and returns its id and URL.

rename_workspace

Renames a workspace you own.

list_workflows

Lists the user's workflow canvases — personal plus any workspace they belong to.

create_workflow

Builds a workflow canvas from a high-level blocks spec (notes + reference assets + generators), ready to Generate.

update_workflow

Renames a workflow and/or appends new blocks below its current content.

get_workflow

Reads a single workflow canvas with its nodes (text, asset, mediaGen, llm, group) and edges.

get_group_media

Resolves a workflow group node into its media items + context notes, with Meta connection status.

Billing

billing_status

Reports your plan, subscription status, and credit balance — and whether generation is enabled.

get_checkout_link

Mints a Stripe checkout link for a plan or credit pack so you can pay without leaving your assistant.

Meta Ads

meta_connection_status

Checks your Meta connection and can list available ad accounts, pages, and pixels.

deploy_meta_ads_plan

Creates or extends a Meta campaign, ad sets, and ads from a plan (supports carousel + dry-run).

list_meta_campaigns

Lists campaigns under your connected ad account, newest first.

list_meta_adsets

Lists the ad sets within a given Meta campaign.

manage_meta_status

Sets ACTIVE / PAUSED / ARCHIVED / DELETED on a campaign, ad set, or ad.

update_meta_budget

Updates the daily or lifetime budget (in cents) on a campaign or ad set.

Available models

Pass any model id below to generate_image or generate_video. Credit costs start from the listed base and rise with resolution, quality, or duration.

Image models

10 models
Modelmodel idFrom credits
GPT Image 2NEW
OpenAI's State-of-the-Art Image Generation
openai/gpt-image-22 cr
Grok ImagineNEW
xAI Grok image generation
xai/grok-imagine-image1 cr
Nano Banana Pro
Google's Flagship Generation Model
google/nano-banana-pro1 cr
GPT Image 1.5NEW
OpenAI's Latest Image Generation
openai/gpt-image-1.52 cr
P-ImageFAST
Fast & High Quality Generation
prunaai/p-image1 cr
Z-Image Turbo Img2ImgFAST
Fast img2img — re-imagines a sketch from your prompt
prunaai/z-image-turbo-img2img1 cr
Seedream 4.5NEW
ByteDance Seedream 4.5
bytedance/seedream-4.52 cr
Seedream 5 LiteNEW
ByteDance Seedream 5.0 Lite with built-in reasoning
bytedance/seedream-5-lite2 cr
Topaz Image UpscaleNEW
Professional-grade image upscaling from Topaz Labs
topazlabs/image-upscale2 cr
FLUX.2 ProPRO
Black Forest Labs FLUX.2 Pro
black-forest-labs/flux-2-pro3 cr

Video models

8 models
Modelmodel idFrom credits
Seedance 2.0NEW
ByteDance multimodal video with native audio
bytedance/seedance-2.021 cr
Grok Imagine Video 1.5NEW
xAI Grok video generation (1.5 with reference image)
xai/grok-imagine-video18 cr
Gemini Omni FlashNEW
Google Gemini Omni Flash video generation & editing
google/gemini-omni-flash31 cr
Veo 3.1NEW
Google's Video Generation Model v3.1
google/veo-3.118 cr
Veo 3.1 LiteNEW
Cost-efficient Veo 3.1 with native audio
google/veo-3.1-lite7 cr
Kling 3.0 OmniNEW
Kling V3 Omni with sound & image/video reference
kwaivgi/kling-v3-omni37 cr
Kling 3.0NEW
Kling V3 with multi-shot, elements & sound
kwaivgi/kling-v337 cr
Kling 3.0 Motion ControlNEW
Motion transfer from reference video onto a character image
kwaivgi/kling-v3-motion-control21 cr

How authentication works

  • 1.Your client opens a browser window to specialx.ai/oauth/authorize.
  • 2.You sign in (or sign up) and approve access. Tokens are stored locally by your client.
  • 3.All requests are scoped to your account. Generations consume credits from your balance — refunded automatically on failure.

FAQ

What is MCP?+
Model Context Protocol is an open standard from Anthropic that lets AI clients talk to external tools and data sources. Any MCP-compatible client can connect to SpecialX with no extra plugin.
Does this cost extra?+
No. The MCP server is free to use — you only pay for the credits your generations consume, at the same rates as the website.
Which transport is used?+
HTTP streamable transport (no SSE). The endpoint speaks the latest MCP spec with OAuth 2.1 (PKCE). SSE-only clients are not supported.
Can I revoke access?+
Yes. Revoke any client's tokens from Settings at any time.
© 2026 SpecialX™. All rights reserved.