mcpField
U
UlazAI Media

UlazAI Media

Remote
ulazai.comMedia & Design0Updated 2w ago

About UlazAI Media

UlazAI Media is an MCP server for UlazAI account holders to create private images through an AI assistant. It matches models and saves generation parameters for confirmation before starting, then returns a file link; retries do not create duplicate images or spend extra credits.

Key features

  1. 01Find suitable image models
  2. 02Save parameters for confirmation
  3. 03Start generation after approval
  4. 04Check allowance and job status
  5. 05Get private image links

Use cases

  1. 01Choose a model for product photos
  2. 02Generate website hero images
  3. 03Check remaining monthly allowance

MCP support

This remote MCP server uses Streamable HTTP to provide tools for account allowance, model search, image preparation, generation, and status checks to MCP clients.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.ulazai.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README
UlazAI Media logo

UlazAI Media MCP server

Create private AI images with your UlazAI account: pick a model, confirm, generate, download.

Remote MCP server: https://mcp.ulazai.com/mcp (Streamable HTTP) · Website: ulazai.com

What it does

UlazAI Media lets an AI assistant create images through your UlazAI account. It first looks up which image models fit the request, saves the exact parameters as a quote, and starts one generation only after you confirm. It then polls until the private file is ready and gives you the link. Every write carries an idempotency key, so a retried call never creates a second image or spends a second credit.

Images are private to your account. The assistant checks your monthly allowance before it starts.

Connect

  • Server URL: https://mcp.ulazai.com/mcp
  • Transport: Streamable HTTP
  • Authentication: OAuth with PKCE (S256), dynamic client registration and client ID metadata documents, so MCP clients connect without manual setup. Sign-in runs through Auth0 with your UlazAI account.

Claude (claude.ai, Desktop): Settings → Connectors → Add custom connector → paste the server URL.

Claude Code:

claude mcp add --transport http ulazai https://mcp.ulazai.com/mcp

Cursor, VS Code, Cline, Windsurf and other clients (mcp.json / cline_mcp_settings.json):

{
  "mcpServers": {
    "ulazai": {
      "type": "http",
      "url": "https://mcp.ulazai.com/mcp"
    }
  }
}

Cline uses "type": "streamableHttp"; see llms-install.md.

Tools

ToolWhat it does
get_ulazai_accountAllowance and credits.
search_ulazai_modelsFind image models that fit a request.
prepare_ulazai_imageSave prompt and parameters as a quote.
create_ulazai_imageStart the generation (after confirmation).
get_ulazai_generationStatus and private file link.

Example prompts

  • Which model should I use for a product photo on a white background?
  • Make a square hero image of a red bicycle against a brick wall.
  • How many images can I still make this month?

Links

Keywords

AI image generator, text to image, product photo AI, model comparison, image generation API, marketing visuals, hero images.

Nederlands: AI afbeelding maken, AI plaatjes genereren, productfoto AI, beeld genereren, afbeeldingen voor website.

More MCP servers by Samautomation

Publisher

Samautomation, Wognum, the Netherlands · https://samautomation.work

This repository holds the public listing (README, server.json, install notes). The server itself is hosted by the publisher; there is nothing to install or build.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.