Ideogram MCP Server

π¦ νλ‘μ νΈ κ°μ
Ideogram API (v3.0)λ₯Ό MCP μλ²λ₯Ό ν΅ν΄ μ¬μ©ν μμλ TypeScript λꡬ
μ΄λ―Έμ§ μμ±, μ€νμΌ μ°Έμ‘°, λ§€μ§ ν둬ννΈ, μ’ ν‘λΉ, λͺ¨λΈ μ ν λ± λ€κΈ°λ₯
Claude Desktop λ° κΈ°ν MCP ν΄λΌμ΄μΈνΈμμ μ¦μ μ¬μ© OK
Related MCP server: OpenAI MCP
β‘οΈ ν΅μ€ννΈ
Claude Desktopμ΄λ λ€λ₯Έ MCP ν΄λΌμ΄μΈνΈμ νμ μ°κ³λ₯Ό μνλ€λ©΄,
μλ JSON μ€ λν«μ μ€μ νμΌμ λ³΅μ¬ OK β¨
{
"mcpServers": {
"ideogram": {
"command": "npx",
"args": [
"@sunwood-ai-labs/ideagram-mcp-server"
],
"env": {
"IDEOGRAM_API_KEY": "your_api_key_here"
}
}
}
}π οΈ MCP ν΄ μ¬μ
generate_image
νλΌλ―Έν° μΌλ(μ΅μ ν)
λ§€κ°λ³μ | κΈν | μ€λͺ | νμ/μ ν | λΉκ³ |
prompt | λ¬Έμμ΄ | μ΄λ―Έμ§ μμ± ν둬ννΈ(μμ΄ κΆμ₯) | νμ | |
aspect_ratio | λ¬Έμμ΄ | μ’ ν‘λΉ(μ: "1x1", "16x9", "4x3" λ±) | μ ν | 15μ’ λ₯ |
resolution | λ¬Έμμ΄ | ν΄μλ(곡μ λ¬Έμ μ°Έμ‘°, μ΄ 69μ’ ) | μ ν | |
seed | integer | λμ μλ(μ¬νμ± λ΄λ³΄μ©) | μ ν | 0ο½2147483647 |
magic_prompt | λ¬Έμμ΄ | λ§€μ§ ν둬ννΈ("AUTO" | "ON" | "OFF") |
rendering_speed | λ¬Έμμ΄ | v3μ© λ λλ§ μλ("TURBO" | "DEFAULT" | "QUALITY") |
style_codes | string[] | 8μ μ€νμΌ μ½λ λ°°μ΄ | μ ν | |
style_type | λ¬Έμμ΄ | μ€νμΌ νμ ("AUTO" | "GENERAL" | "REALISTIC" |
negative_prompt | λ¬Έμμ΄ | μ μΈ μμ(μμ΄ κΆμ₯) | μ ν | |
num_images | number | μμ± μ΄λ―Έμ§ μ(1~8) | μ ν | |
style_reference | κ°μ²΄ | μ€νμΌ μ°Έμ‘°(Ideogram 3.0 μλ‘μ΄ κΈ°λ₯) | μ ν | μλ μμΈ |
β urls | string[] | μ°Έμ‘° μ΄λ―Έμ§ URL λ°°μ΄(μ΅λ 3κ°) | μ ν | |
β style_code | λ¬Έμμ΄ | μ€νμΌ μ½λ | μ ν | |
β random_style | λΆμΈ | λλ€ μ€νμΌ μ¬μ© | μ ν | |
output_dir | λ¬Έμμ΄ | μ΄λ―Έμ§ μ μ₯ λλ ν 리(κΈ°λ³Έκ°: "docs") | μ ν | |
base_filename | λ¬Έμμ΄ | μ μ₯ νμΌ μ΄λ¦μ κΈ°λ°(κΈ°λ³Έκ°: "ideogram-image") | μ ν | νμμ€ν¬νγ»ID λΆμ¬ |
blur_mask | λΆμΈ | μ΄λ―Έμ§ κ°μ₯μ리 νλ¦Ό(trueλ‘ λ§μ€ν¬ ν©μ±) | μ ν | κΈ°λ³Έκ°: false |
π μ¬μ© μ
const result = await use_mcp_tool({
server_name: "ideagram-mcp-server",
tool_name: "generate_image",
arguments: {
prompt: "A beautiful sunset over mountains",
aspect_ratio: "16x9",
rendering_speed: "QUALITY",
num_images: 2,
style_reference: {
urls: [
"https://example.com/ref1.jpg",
"https://example.com/ref2.jpg"
],
random_style: false
},
blur_mask: true
}
});π§βπ» κ°λ°, λΉλ, ν μ€νΈ
npm run buildnpm run watch... κ°λ° λͺ¨λ(μλ λΉλ)npm run lint... μ½λ λ¦°νΈnpm test... ν μ€νΈ μ€ν
ποΈ λλ ν 리 ꡬμ±
ideagram-mcp-server/
βββ assets/
βββ docs/
β βββ ideogram-image_2025-05-18T06-31-45-777Z.png
βββ src/
β βββ tools/
β βββ types/
β βββ utils/
β βββ ideogram-client.ts
β βββ index.ts
β βββ server.ts
β βββ test.ts
βββ .env.example
βββ package.json
βββ tsconfig.json
βββ README.md
βββ ...οΌηη₯οΌπ κΈ°μ¬
μ΄ μ μ₯μλ₯Ό ν¬ν¬
μλ‘μ΄ λΈλμΉ μμ± (
git checkout -b feature/awesome)λ³κ²½ μ»€λ° (μ»€λ° λ©μμ§λ μΌλ³Έμ΄ + μ΄λͺ¨ν°μ½ μΆμ²!)
νΈμ & νλ¦ λ§λ€κΈ°
π λ°°ν¬ λ° μΆμ
GitHub Actionsμμ μλ npm 곡κ°
λ²μ μ λ°μ΄νΈ β νκ·Έ pushλ‘ μλ λ°°ν¬
npm version patch|minor|major
git push --follow-tagsμμΈν λ΄μ©μ docs/npm-deploy.md λ₯Ό μ°Έμ‘°νμμμ€!
π λΌμ΄μΌμ€
MIT
Available Tools
1 toolgenerate_imageC
Generate an image using Ideogram AI
Inputs: prompt (required), aspect_ratio, resolution, seed, +11 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The single tool 'generate_image' has a clearly distinct and unambiguous purpose.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'generate_image' follows a clear verb_noun pattern.
One tool is too few for a server named 'Ideogram MCP Server', which suggests a broader scope for image generation or AI tasks. A single tool feels thin and limited for such a domain.
The tool surface is severely incomplete for an image generation server. It only offers generation with no options for editing, listing, deleting, or managing images, creating significant gaps in functionality.
Maintenance
Related MCP Connectors
MCP server for Qwen Image 3 AI image generation
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models. Up to 4 images per call, SVG vectorization, background removal, upscaling and image-to-video. Remote MCP with OAuth, no API keys.
Generate AI images and videos from any compatible MCP client.
MCP server for Flux AI image generation
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA server that provides AI-powered image generation, modification, and processing capabilities through the Model Context Protocol, leveraging Google Gemini models and other image services.19MIT
- AlicenseNot gradedqualityFmaintenanceA Model Context Protocol server enabling AI assistants to generate images through OpenAI's DALL-E API with full support for all available options and fine-grained control.1MIT
- AlicenseDqualityNot gradedmaintenanceA Model Context Protocol server that provides image generation capabilities using Google's Gemini 2 API, allowing users to generate multiple images with customizable parameters like prompts, aspect ratios, and person generation settings.16MIT
- AlicenseDqualityDmaintenanceA Model Context Protocol server that enables generating and editing images using OpenAI's gpt-image-1 model, allowing AI assistants to create and modify images from text prompts.218MIT