AI Manga & Anime Generator - Mangii MCP

Create manga story

manga.create_story

Start a new private manga (panel 1). Required: prompt + style_id from manga.list_styles. Optional identity_image or reference_image is Image 1. Style locks. Default async=false returns image_url, story_id, panel_id. Then manga.continue_story. Costs 1/2/5 credits by quality.

Input Schema

TableJSON Schema

Name	Required	Description
`async`	No	On this MCP server the default is false: wait and return image_url in one call. Set true only if you will poll manga.get_job. HTTP API default remains async.
`title`	No	Optional story title shown in the library. Example: "Rain Duel". Omit to let Mangii name it.
`prompt`	Yes	Scene in everyday language: characters, place, action, mood, camera, weather, color or black-and-white. Example: "A duel under cherry blossoms, low angle, rain, full color." Max 2000 characters.
`quality`	No	Generation quality. standard costs 1 credit, hd 2, ultra 5. Default standard. HD/Ultra need an unlocked API wallet.
`style_id`	Yes	Canonical style id from manga.list_styles. Example: classic_shonen or cinematic_anime. Locked after panel 0.
`identity_image`	No	Replacement photo: https URL or data:image/...;base64,... URI. Public hosts only. Same slot cannot also send a panel id.
`idempotency_key`	No	Optional. Reuse the same key on retry so a timeout does not charge twice. 8-200 chars. Omit to mint a one-shot key (unsafe on retry).
`reference_image`	No	Optional first-panel identity photo. https URL or data URI. Alias of identity_image.

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Machine error code such as invalid_request, insufficient_credits, or quality_forbidden.
`job_id`	No	Async job id when async is true or the work is still running.
`message`	No	Human-readable error. Never includes stack traces or internal paths.
`quality`	No	Quality used for this generation.
`panel_id`	No	Generated or regenerated panel id.
`story_id`	No	Created or existing story id.
`image_url`	No	HTTPS URL of the finished panel when async is false and generation succeeded.
`next_step`	No	What the agent should call next. Follow this instead of guessing.
`request_id`	No	Request correlation id.
`credits_charged`	No	API credits billed for a successful generation.
`credits_remaining`	No	Remaining spendableCredits after the call (apiPack plus packCredits after a purchase).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 6, 2026

changedOutput schema / properties / credits_remaining / description

Previous value: -"Remaining spendableCredits after the call (apiPack plus purchase-backed packs)."New value: +"Remaining spendableCredits after the call (apiPack plus packCredits after a purchase)."

Changed2 schema fields changedAug 23, 2026

addedInput schema / properties / idempotency_key

Added value: +{
+  "description": "Optional. Reuse the same key on retry so a timeout does not charge twice. 8-200 chars. Omit to mint a one-shot key (unsafe on retry).",
+  "maxLength": 200,
+  "minLength": 8,
+  "type": "string"
+}

changedOutput schema / properties / credits_remaining / description

Previous value: -"Remaining apiPackCredits after the call."New value: +"Remaining spendableCredits after the call (apiPack plus purchase-backed packs)."

Changed2 schema fields changedAug 23, 2026

addedInput schema / properties / identity_image

Added value: +{
+  "description": "Replacement photo: https URL or data:image/...;base64,... URI. Public hosts only. Same slot cannot also send a panel id.",
+  "type": "string"
+}

addedInput schema / properties / reference_image

Added value: +{
+  "description": "Optional first-panel identity photo. https URL or data URI. Alias of identity_image.",
+  "type": "string"
+}

AddedAug 23, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations indicate a non-readonly, non-idempotent operation. The description adds crucial behavior: style locking, default async behavior, credit costs, and the returned fields (image_url, story_id, panel_id). No contradiction with annotations; it enriches them.

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

Conciseness5/5

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

The description is a single, dense sentence that front-loads the core purpose and required inputs, then covers async, credits, and next step. No wasted words; every phrase carries meaning.

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?

For a tool with a rich schema and an output schema, the description covers all essential operational details: required params, cost model, async behavior, and the natural next step (continue_story). Nothing needed for correct invocation is missing.

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 coverage is 100%, with detailed descriptions for each parameter (e.g., quality costs, style_id source, identity_image alias). The description adds only marginal context beyond the schema, so the baseline 3 is appropriate.

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 ('Start a new private manga') and resource (panel 1), clearly distinguishing it from siblings like continue_story. It also specifies required parameters and the flow, leaving no ambiguity about what the tool does.

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?

Explicitly states when to use: to create the first panel, and points to the alternative 'manga.continue_story' for subsequent panels. It also references list_styles for style_id, giving clear context for selection among siblings.

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

All AI Manga & Anime Generator - Mangii MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.