Skip to main content
Glama

Magic Hour

by ai.magichour.mcp

ai_image_generator_create_image

Create an AI image with advanced model selection and quality controls.

MCP guidance:

  • This starts an async image generation job and returns id plus credits_charged immediately. If the user wants the finished result, call the wait_for_image_project helper with the returned id, or poll the matching GET /v1/image-projects/{id} endpoint until status is complete, error, or canceled. Completed projects include downloads with direct URLs. The custom wait helper also returns exact_download_urls separately from expiration metadata.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoGive your image a custom name for easy identification.Ai Image - dateTime
modelNoThe AI model to use for image generation. Each model has different capabilities and costs. **Models:** - `default` - Use the model we recommend, which will change over time. This is recommended unless you need a specific model. This is the default behavior. - `flux-2-klein` - from 5 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: free, creator, pro, business - Image count allowed: 1 - `flux-schnell` - from 5 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: free, creator, pro, business - Image count allowed: 1, 2, 3, 4 - `gpt-image-2` - from 50 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Image count allowed: 1, 2, 3, 4 - `nano-banana` - from 50 credits/image - Supported resolutions: 640px, 1k - Available for tiers: creator, pro, business - Image count allowed: 1, 2, 3, 4 - `nano-banana-2` - from 100 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Image count allowed: 1, 4, 9, 16 - `nano-banana-2-lite` - from 50 credits/image - Supported resolutions: 640px, 1k - Available for tiers: creator, pro, business - Image count allowed: 1, 2, 3, 4 - `nano-banana-pro` - from 150 credits/image - Supported resolutions: 1k, 2k, 4k - Available for tiers: creator, pro, business - Image count allowed: 1, 4, 9, 16 - `seedream-v4` - from 40 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Image count allowed: 1, 2, 3, 4 - `seedream-v5-pro` - from 75 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: creator, pro, business - Image count allowed: 1, 2, 3, 4 - `z-image-turbo` - from 5 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: free, creator, pro, business - Image count allowed: 1, 2, 3, 4 **Deprecated Enum Values:** - `seedream` - Use `seedream-v4` instead.
styleYesThe art style to use for image generation.
resolutionNoMaximum resolution (longest edge) for the output image. **Options:** - `640px` — up to 640px - `1k` — up to 1024px - `2k` — up to 2048px - `4k` — up to 4096px - `auto` — **Deprecated.** Mapped server-side from your subscription tier to the best matching resolution the model supports **Per-model support:** - `flux-2-klein` - 640px, 1k, 2k - `flux-schnell` - 640px, 1k, 2k - `gpt-image-2` - 640px, 1k, 2k, 4k - `nano-banana` - 640px, 1k - `nano-banana-2` - 640px, 1k, 2k, 4k - `nano-banana-2-lite` - 640px, 1k - `nano-banana-pro` - 1k, 2k, 4k - `seedream-v4` - 640px, 1k, 2k, 4k - `seedream-v5-pro` - 640px, 1k, 2k - `z-image-turbo` - 640px, 1k, 2k Note: Resolution availability depends on the model and your subscription tier.auto
image_countYesNumber of images to generate. Maximum varies by model.
aspect_ratioNoThe aspect ratio of the output image(s). If not specified, defaults to `1:1` (square).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesUnique ID of the image. Use it with the [Get image Project API](https://docs.magichour.ai/api-reference/image-projects/get-image-details) to fetch status and downloads.
credits_chargedYesThe amount of credits deducted from your account to generate the image. We charge credits right when the request is made. If an error occurred while generating the image(s), credits will be refunded and this field will be updated to include the refund.

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full disclosure burden. It clearly states the async behavior, immediate return of id and credits_charged, and the polling workflow. It could mention failure/error handling or rate limits, but it covers the most important behavioral trait (async job lifecycle) well.

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 main description is two sentences, front-loaded with the core purpose, followed by a compact MCP guidance block. Every sentence earns its place. The long model list lives in the schema, not the description, so the description itself remains appropriately sized.

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?

Given the rich input schema (100% parameter coverage) and the existence of an output schema, the description's job is mainly to explain the async workflow and result retrieval, which it does well. Minor gaps: it doesn't mention credit cost variation or possible error handling, but the essential operational flow is covered.

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 framing the tool around 'advanced model selection', signaling that model choice is important and that pricing/capabilities vary. It also explains the async consequence of submitted parameters (returns id immediately), which is not in the schema.

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 states a specific verb and resource: 'Create an AI image with advanced model selection and quality controls.' It clearly distinguishes this from sibling tools with more focused scope (e.g., ai_image_upscaler_create_image, ai_image_editor_create_image) by positioning it as the general creation tool.

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

Usage Guidelines5/5

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

The MCP guidance explicitly explains that this starts an async job and tells the agent exactly what to do next: call wait_for_image_project with the returned id or poll the endpoint until terminal status. This is clear when-to-use and how-to-proceed guidance that is not available from sibling tool names alone.

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

All Magic Hour toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation3/5

Most tools are differentiated by product-specific prefixes (e.g., lip_sync, text_to_video, image_upscaler), but the set contains many overlapping create_image/create_video tools, and generic editors like ai_image_editor_create_image and ai_video_editor_create_video blur boundaries with their more specific counterparts. Face/body swapping tools also occupy a similar conceptual space, requiring careful description reading to avoid misselection.

Naming Consistency4/5

Names generally follow a descriptive snake_case pattern of feature plus action (e.g., text_to_video_create_video, image_projects_delete, wait_for_image_project). Minor inconsistencies like ai_face_editor_edit_image versus the dominant create_image suffix, and the mixed ai_ prefix usage across tools, prevent a perfect score.

Tool Count2/5

44 tools is a large surface for an MCP server, even for a broad media-generation API. The count exceeds the 25+ threshold and creates a heavy selection burden, especially with over a dozen create tools for images and videos.

Completeness4/5

The surface covers the full create-to-download workflow for image, video, and audio: creation, status polling, wait helpers, fetch helpers, delete, and asset upload support. Minor gaps include no list/cancel endpoints and no general project search, but agents can complete core tasks without dead ends.

Resources