Skip to main content
Glama
alexlivre

minimax-image-mcp

by alexlivre
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Generate Image (MiniMax)

minimax_image_generate

Generate images from text prompts with adjustable aspect ratios, batch sizes, seed control, and image-to-image character references.

Instructions

Generate images from text prompts using MiniMax's image-01 model. Supports multiple aspect ratios, batch generation (1-9 images), image-to-image with character references, prompt optimization, and seed-based reproducibility. Images are saved to disk and file paths are returned.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nNoNumber of images to generate (1-9). Using 9 is 8x faster than 9 separate calls.
seedNoSeed for reproducibility. Same seed + same parameters = same image.
promptYesImage description to generate. Max 1500 characters.
output_dirNoDirectory to save images. Must be within the working directory or MINIMAX_OUTPUT_DIR. Default: ./output/
aspect_ratioNoImage aspect ratio. Options: 1:1, 16:9, 4:3, 3:2, 2:3, 3:4, 9:16, 21:91:1
response_formatNoResponse format. 'base64' for persistence (recommended), 'url' expires in 24h.base64
prompt_optimizerNoEnable automatic prompt optimization. May add extra elements.
subject_referenceNoReference images for Image-to-Image. Maintains visual identity of the character.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYes
failuresNo
metadataYes
file_pathsYes
image_countYes
saved_countYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv1.0.3
    • changedInput schema / properties / aspect_ratio / description
      Previous value: -"Proporção da imagem. Opções: 1:1, 16:9, 4:3, 3:2, 2:3, 3:4, 9:16, 21:9"New value: +"Image aspect ratio. Options: 1:1, 16:9, 4:3, 3:2, 2:3, 3:4, 9:16, 21:9"
    • changedInput schema / properties / n / description
      Previous value: -"Número de imagens a gerar (1-9). Usar 9 é 8× mais rápido que 9 chamadas separadas."New value: +"Number of images to generate (1-9). Using 9 is 8x faster than 9 separate calls."
    • changedInput schema / properties / output_dir / description
      Previous value: -"Diretório para salvar imagens. Padrão: ./output/ ou MINIMAX_OUTPUT_DIR"New value: +"Directory to save images. Must be within the working directory or MINIMAX_OUTPUT_DIR. Default: ./output/"
    • changedInput schema / properties / prompt / description
      Previous value: -"Descrição da imagem a gerar. Máximo 1500 caracteres."New value: +"Image description to generate. Max 1500 characters."
    • changedInput schema / properties / prompt_optimizer / description
      Previous value: -"Ativa otimização automática do prompt. Pode adicionar elementos extras."New value: +"Enable automatic prompt optimization. May add extra elements."
    • changedInput schema / properties / response_format / description
      Previous value: -"Formato de resposta. 'base64' para persistência (recomendado), 'url' expira em 24h."New value: +"Response format. 'base64' for persistence (recommended), 'url' expires in 24h."
    • changedInput schema / properties / seed / description
      Previous value: -"Seed para reprodutibilidade. Mesmo seed + mesmos parâmetros = mesma imagem."New value: +"Seed for reproducibility. Same seed + same parameters = same image."
    • changedInput schema / properties / subject_reference / description
      Previous value: -"Imagens de referência para Image-to-Image. Mantém identidade visual do personagem."New value: +"Reference images for Image-to-Image. Maintains visual identity of the character."
  2. First observedv1.0.0

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (which are not very informative), the description discloses that images are saved to disk and file paths returned, and that prompt optimization may add extra elements. It does not cover rate limits or potential side effects, but adds useful behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single paragraph covering all key features. It is fairly concise but could be slightly more structured (e.g., bullet points) for easier scanning. Still, it is efficient and well written.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool complexity (8 parameters, 100% schema coverage, multiple features), and the presence of an output schema, the description is complete. It mentions file path returns and covers all major capabilities.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the speed benefit of n=9, expiry difference between 'url' and 'base64', and the effect of prompt_optimizer. This goes beyond the schema definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it generates images from text prompts using a specific model, and enumerates supported features (aspect ratios, batch generation, etc.). It is specific and distinguishes the tool from any potential alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context like recommending n=9 for speed, but does not explicitly state when to use this tool versus alternatives. Since no siblings are listed, it is still clear, but lacks explicit when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools