Skip to main content
Glama

LemGen AI Design MCP

Open-source MCP server for AI image and video creation. Search a curated LemGen prompt library, enhance rough ideas into production prompts, and generate images or videos from Claude Code, Cursor, Codex, Windsurf, Roo Code, OpenClaw, Hermes Agent, and any MCP-compatible host.

Free tools work without an API key. Generation tools require a LemGen API key from https://lemgen.org.

Features

Tool

Free

Purpose

search_gallery

Yes

Search curated image/video prompts with preview URLs.

get_inspiration

Yes

Fetch the full prompt, metadata, media, and source link.

enhance_prompt

Yes

Expand a short idea into a professional prompt.

list_models

Yes

Browse LemGen model capabilities.

prompt_tools

Yes

Translate, polish, or improve prompts.

manage_preferences

Yes

Store local style/model preferences.

generate_image

Token

Generate an image with LemGen.

generate_video

Token

Generate a video with LemGen.

Related MCP server: mediamcp

Quick Start

{
  "mcpServers": {
    "lemgen": {
      "command": "npx",
      "args": ["-y", "lemgen@latest"]
    }
  }
}

To enable generation:

{
  "mcpServers": {
    "lemgen": {
      "command": "npx",
      "args": ["-y", "lemgen@latest"],
      "env": {
        "LEMGEN_API_TOKEN": "sk_..."
      }
    }
  }
}

Claude Code Plugin

/plugin marketplace add gptimage2prompts/lemgen-ai-design-mcp
/plugin install lemgen@lemgen-marketplace

Restart Claude Code after installation.

Cursor / Codex / Windsurf / Roo Code

Add the MCP server to your host config:

{
  "mcpServers": {
    "lemgen": {
      "command": "npx",
      "args": ["-y", "lemgen@latest"],
      "env": {
        "LEMGEN_API_TOKEN": "sk_..."
      }
    }
  }
}

OpenClaw

Use openclaw/SKILL.md with the MCP config above, or install the packaged plugin once published to your preferred OpenClaw bundle registry.

Prompt Library

Prompt data lives in data/trending-prompts.json and can be refreshed from the companion repository lemgen-trending-prompts.

Each item includes:

  • id

  • prompt

  • model

  • categories

  • preview image/video URL

  • engagement fields

  • source_url linking back to LemGen

Environment Variables

Variable

Description

LEMGEN_API_BASE_URL

Defaults to https://lemgen.org.

LEMGEN_API_TOKEN

API key for generation tools.

LEMGEN_OUTPUT_DIR

Local image output directory for future CLI workflows.

LEMGEN_VIDEO_OUTPUT_DIR

Local video output directory for future CLI workflows.

LEMGEN_PREFERENCES_PATH

Local preferences JSON path.

Development

pnpm install
pnpm build
pnpm inspect

License

MIT

Available Tools

8 tools
enhance_promptA
Read-only

Turn a short idea into a professional image/video prompt. Free, local, no API key required.

Inputs: idea (required), style, mediaType, aspectRatio, +1 more.

generate_imageA

Generate an AI image with LemGen. Requires LEMGEN_API_TOKEN. Use after the user approves a final prompt.

Inputs: prompt (required), wait, model, quality, +5 more.

generate_videoB

Generate an AI video with LemGen. Requires LEMGEN_API_TOKEN. Videos are slow and should only be called after explicit user confirmation.

Inputs: prompt (required), tier, wait, model, +7 more.

get_inspirationA
Read-only

Get the full prompt, preview media, metadata, and LemGen source link for one gallery entry. Free, no API key required.

Inputs: id (required).

list_modelsA
Read-only

List LemGen image and video models with strengths, ratios, resolutions, and reference limits. Free, no API key required.

Inputs: mediaType.

manage_preferencesA

Read or update local LemGen preferences for style, model, aspect ratio, resolution, and favorite prompt ids. Free, local, no API key required.

Inputs: action (required), model, style, promptId, +3 more.

prompt_toolsC
Read-only

Translate, polish, or improve an AI image/video prompt. Free locally; if LEMGEN_API_TOKEN is configured, the LemGen prompt tool may be used by callers separately.

Inputs: text (required), action (required), mediaType, targetLanguage.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 8 tools

    Disambiguation3/5

    Most tools are distinct, but 'enhance_prompt' and 'prompt_tools' both improve prompts, creating potential confusion. Descriptions help somewhat but overlap remains.

    Naming Consistency4/5

    Seven of eight tools follow a clear verb_noun pattern. The exception is 'prompt_tools' (noun_noun), a minor deviation from the otherwise consistent naming.

    Tool Count5/5

    With 8 tools covering prompt enhancement, generation, gallery search, inspiration, model listing, and preferences, the count is well-scoped for a design server.

    Completeness4/5

    Core workflows (prompt creation, generation, exploration) are covered. Missing tools for deleting generated media or managing a user's own library, but these are plausible gaps.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      mediamcp is an MCP server that connects your AI assistant — Claude Code, Claude Desktop, Cursor, Windsurf, VS Code, or anything else that speaks MCP — to cloud media models (Gemini Flash Image, GPT-5 Image, Seedream, Veo, Sora, …) via OpenRouter or any OpenAI-compatible API.
      6
      74 npm
      4
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      An open-source MCP server that connects AI clients to ImgLume for visual inspiration, prompt improvement, image generation and editing, and video generation.
      6
      1
      MIT