Skip to main content
Glama

MiniMax MCP Server by useapi.net (third-party)

Generate images

minimax_create_image

Generate 1-4 images on hailuoai.video with image-01, MiniMax H3 Image (h3-image, -highspeed), Nano Banana 2 / Pro, GPT Image 1.5 / 2, Seedream 4.5 / 5.0 or Midjourney V7 / Niji 7 (always 4), from a prompt and up to 16 reference images (referenceFileIdN, cited as @ImageN on models that support it) or a character image (characterFileId, image-01). Uses MiniMax credits per image. Waits up to ~50 s and returns each image's URL and fileID, the first as an image; else the imageIds for minimax_get_image. POST /images/create.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "minimax_create_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
waitNoWait up to ~50 s for the job to finish (default true); false returns the id at once.
modelNoDefault image-01.
promptYesWhat the image shows. Up to 2,000 characters (5,000 on Midjourney; 7,500 on h3-image, gpt-image-2 and Nano Banana).
accountNoThe account id from minimax_list_accounts. Optional with one account or when a reference fileID names it, required otherwise.
qualityNogpt-image-2 only: low (default), medium, high.
quantityNoImages to make, 1-4 (default 1; Midjourney always 4). Each image is charged.
replyRefNoOptional reference of yours, stored and returned with the result and webhook. Up to 1,024 characters.
replyUrlNoOptional webhook: the API POSTs the finished result (same shape as the get tool's record) to this URL. Up to 1,024 characters.
resolutionNoBy model: image-01 HD; h3-image*, gpt-image-2, nano-banana-pro 1K (default) / 2K / 4K; nano-banana-2 512P (default) / 1K / 2K / 4K; gpt-image-1.5 Low (default) / Medium / High; seedream-4.5 2K / 4K; seedream-5.0 2K / 3K; none on Midjourney.
aspectRatioNoDefault auto (16:9 on image-01 and gpt-image-2, which take no auto). gpt-image-1.5: auto, 1:1, 3:2, 2:3 only; image-01: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9.
characterFileIdNoimage-01 only: a clear front-facing character photo: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId1NoreferenceFileId1: reference image 1, cited as @Image1 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId2NoreferenceFileId2: reference image 2, cited as @Image2 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId3NoreferenceFileId3: reference image 3, cited as @Image3 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId4NoreferenceFileId4: reference image 4, cited as @Image4 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId5NoreferenceFileId5: reference image 5, cited as @Image5 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId6NoreferenceFileId6: reference image 6, cited as @Image6 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId7NoreferenceFileId7: reference image 7, cited as @Image7 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId8NoreferenceFileId8: reference image 8, cited as @Image8 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId9NoreferenceFileId9: reference image 9, cited as @Image9 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId10NoreferenceFileId10: reference image 10, cited as @Image10 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId11NoreferenceFileId11: reference image 11, cited as @Image11 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId12NoreferenceFileId12: reference image 12, cited as @Image12 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId13NoreferenceFileId13: reference image 13, cited as @Image13 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId14NoreferenceFileId14: reference image 14, cited as @Image14 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId15NoreferenceFileId15: reference image 15, cited as @Image15 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
referenceFileId16NoreferenceFileId16: reference image 16, cited as @Image16 where the model supports @-mentions; fill slots in order from 1 (up to 16 on h3-image / gpt-image-2, 14 on most, 3 on gpt-image-1.5; not image-01): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
promptOptimizationNoLet MiniMax rewrite the prompt (default true).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only say non-read-only, open-world, non-idempotent, non-destructive. The description adds genuinely new behavior: each image consumes MiniMax credits, quantity up to 4 with Midjourney forced to 4, an approximate 50 s blocking window, and the exact return shape (per-image URL and fileID, first image returned as an image, otherwise imageIds).

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?

A single front-loaded paragraph that leads with the action and model list, then constraints, then return behavior and endpoint. The model enumeration is long but earns its place for model selection; a couple of clauses (credits, wait) could be split for scannability.

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

Completeness4/5

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

For a 28-parameter generation tool with no output schema, the description covers cost, sync/async behavior, and return values, which is what an agent most needs. It stops short of describing failure or timeout outcomes after the ~50 s wait, which is the main remaining unknown.

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

Parameters3/5

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

Schema description coverage is 100%, so model gates, resolution and aspect-ratio defaults, prompt length limits, and reference-slot ordering are already documented per-parameter. The description mostly restates that content, adding only the credit-cost note and the @ImageN citation convention, so the baseline of 3 applies.

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 opens with a concrete verb and resource ('Generate 1-4 images') plus the endpoint and provider, and enumerates the exact models accepted. It also distinguishes itself from minimax_get_image by explaining that non-waited jobs yield imageIds for retrieval via that sibling.

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?

It gives clear operative conditions: use wait=true to block ~50 s for URLs, wait=false to return an id immediately and poll with minimax_get_image, and it notes characterFileId is image-01-only while referenceFileIdN must be filled in order. It does not state when to prefer this tool over other creation tools (video/music/speech), but those are obviously different media, so the gap is minor.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources