
Connect Playground AI to ChatGPT, Claude and Gemini
Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn text prompts into high-resolution assets directly in your workflow.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Your AI does the work. We keep it safe and sound.
No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.
Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

Each Connector runs inside its own sealed environment.
Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.
One switch stops every agent. Instantly.
One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.
Spending limits that pause instead of surprise.
Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.
Three controls, built into the layer your AI connects through.
Curated set · 10 capabilities
We ship only the actions that matter.
01-04
4 capabilities in this set.
Part of 10 available through Playground AI.
- 01
List generations
Retrieves your recent image history. It returns generation IDs, the prompts used, and timestamps.
- 02
Outpaint image
Expands an image beyond its original borders. You provide a prompt, a URL, and a direction like up, down, left, or right.
- 03
Remove background
Isolates a subject by stripping away the background. It returns a transparent PNG based on the image URL you provide.
- 04
Transform image
Modifies an existing image using a text prompt. You can control the intensity of the change by setting a strength value between 0 and 1.
05-07
3 capabilities in this set.
Part of 10 available through Playground AI.
- 05
Upscale image
Increases the resolution and detail of an image. You can choose to scale the input by a factor of 2 or 4.
- 06
List models
Shows the available AI models. This includes their names, descriptions, and specific capabilities.
- 07
Generate image
Creates new images from text prompts. You specify the model, width, and height to trigger the render.
08-10
3 capabilities in this set.
Part of 10 available through Playground AI.
- 08
Generate with controlnet
Uses structural guidance to shape a new image. It supports control types like canny, depth, pose, and scribble.
- 09
Get generation
Fetches specific details for a single generation. It returns the resulting images, the prompt, and metadata.
- 10
Inpaint image
Edits specific parts of an image using a mask. You provide the image URL and a mask URL to define the edit area.
Real work
What teams actually run
UI Asset Creation
Generate specific icons or background textures for web layouts directly from your code editor.
Rapid Prototyping
Create visual concepts for mood boards by describing them to your agent.
Image Repair
Fix specific flaws in a photo by using inpainting to replace unwanted elements.
Content Expansion
Take a portrait and use outpainting to turn it into a wide landscape shot.
Automate a task
Put Playground AI to work on one thing.
Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.
One connector, every AI
Playground AI works with the most popular AI clients.
These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put Playground AI to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.
Observed, not estimated
938ms average. Fast in production.
Playground AI is checked daily against the live service.
- Fastest day
- 821ms
- Slowest day
- 1158ms
- 14-day trend
- Slowing+5%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Playground AI, so you can see the experience inside your AI.
It does not authenticate your account with Playground AI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Playground AI Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_CZ4iZgNPLcXoXLZeQcrF98W9DBO3Kd80p4W5elUg/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Playground AI capabilities are ready to use.
{
"mcpServers": {
"playground-ai-mcp": {
"url": "https://edge.vinkius.com/vk_preview_CZ4iZgNPLcXoXLZeQcrF98W9DBO3Kd80p4W5elUg/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
Guided setup for Claude? Set up Playground AI in Claude and other AIs
Who it's for
Built for the work Playground AI owners hand off.
This MCP is for technical creatives who want to stay in their primary workspace while generating high-end visuals.
- 01
Web Developers
They use it to generate perfectly sized UI placeholders and graphical assets without leaving their IDE.
- 02
Concept Artists
They automate tedious tasks like masking and background removal through chat.
- 03
Creative Directors
They use it to quickly upscale or outpaint images while reviewing design work.
FAQ
Questions Playground AI owners ask.
- 01
How do I use this MCP?
Once connected, you simply tell your AI client what you want to do, such as 'generate an image' or 'remove the background from this URL'.
- 02
Which AI clients are compatible?
This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.
- 03
Do I need my own GPU?
No, the processing happens on Playground AI's compute clusters, not your local machine.
- 04
Can I control the size of the images?
Yes, you can specify dimensions like 1024x1024 in your instructions to the agent.
- 05
What happens if I want to change an existing image?
You can use the transform_image capability for general changes or inpaint_image for specific area edits using a mask.
- 06
Can my AI automatically remove a background and embed the image into my project?
Yes! The agent triggers the remove_background method on any public image URL. Playground internally isolates the core subject, dropping the background layers, and replies with a secure pointer URL. Your agent can instantly fetch the response string and code an `` tag placing the clean asset directly into the UI mapping you're developing.
- 07
How exactly does outpaint_image expand the canvas?
The capability passes the target image alongside the literal specific expansion vectors ('up', 'down', 'left', 'right') and a guiding context text. The diffusion nodes generate purely new mathematical tensor states radiating outward, predicting the lighting, shadows, and environment strictly following your prompt rules without stretching existing pixels.
- 08
Can I enforce specific structural references using ControlNet constraints?
Yes. Instead of standard generation, invoke generate_with_controlnet. You upload a scribble or an edges-only mapping layout as your source. By defining the explicit type ('canny', 'depth', 'pose', 'scribble'), the AI strictly anchors its conceptual render to those physical guiding constraints rather than randomizing spatial architecture.
Explore
More in AI Frontier
Midjourney AI (Generative Image Arts) AI Connector
Generate professional AI art via Midjourney — use 'imagine' for text-to-image, upscale grids, and perform came
ViewLuma AI (Generative Video & Creative) AI Connector
Generate cinematic AI videos and images via Luma — use Dream Machine for text-to-video, image-to-video, and pr
ViewLeonardo.ai (Generative AI & Models) AI Connector
Generate high-fidelity images via Leonardo.ai — orchestrate generations, audit AI models, and manage visual as
ViewKling AI (Generative Video & Image) AI Connector
Generate cinematic videos and images via Kling AI — use text-to-video, image-to-video, and AI virtual try-on.
View
Suggestions
Adobe Firefly AI Connector
Generate images and vectors via Adobe Firefly — perform generative fill and expand, create text effects, and r
ViewIdeogram (AI Image Generation) AI Connector
Generate and edit images via Ideogram — the industry leader for rendering text within AI-generated visuals.
ViewImage Router AI Connector
Route image generation requests to the best AI model automatically based on prompt type, style, and quality re
ViewImage Generation Economics AI Connector
Calculate image generation costs, storage scaling, and quality-cost trade-offs.
View
Connect Playground AI to Claude, Cursor, ChatGPT & more
