Ideogram
Verified IntegrationClient Configuration
— Connect Ideogram to Claude Desktop or Cursor in seconds{
"mcpServers": {
"ideogram-1": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-ideogram-1"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Generate images using locally-hosted Ideogram 4 models through a minimal, one-command server.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Ideogram
You need an NVIDIA CUDA-compatible GPU with sufficient VRAM (typically 12-16GB+), Python 3.10+, and at least 25 GB of free SSD space for storing the downloaded model weights. A Hugging Face account and token are also mandatory for model access.
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.