Skip to main content
Glama

AI Manga & Anime Generator - Mangii MCP

by ai.mangii

Regenerate manga panel

manga.regenerate_panel

Redraw or edit one panel. Style stays locked. Same Image 1 / Image 2 ref overrides as manga.continue_story. Get ids from manga.list_panels. Costs the same credits as a new panel.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
asyncNoOn 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.
promptNoOptional rewrite of the scene. Same prompt rules as create. Omit to retry the stored prompt.
qualityNoGeneration quality. standard costs 1 credit, hd 2, ultra 5. Default standard. HD/Ultra need an unlocked API wallet.
panel_idYesPanel id from a previous generate result or manga.list_panels. Example: the panel_id returned by manga.create_story.
story_idYesStory id from manga.create_story. Example: a Firestore story document id returned as story_id.
identity_imageNoReplacement photo: https URL or data:image/...;base64,... URI. Public hosts only. Same slot cannot also send a panel id.
idempotency_keyNoOptional. 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_imageNoAlias for identity_image. Replaces Image 1 with an uploaded photo or URL.
continuity_imageNoReplacement Image 2 (scene) photo: https URL or data URI. Do not also send continuity_panel_id.
context_panel_idsNoLegacy list override [identity_panel_id, scene_panel_id]. Ignored when identity_* or continuity_* fields are set. Prefer those named slots.
identity_panel_idNoOverride Image 1 (identity) with this panel id from manga.list_panels. Do not also send identity_image.
continuity_panel_idNoOverride Image 2 (scene) with this panel id from manga.list_panels. Do not also send continuity_image.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNoMachine error code such as invalid_request, insufficient_credits, or quality_forbidden.
job_idNoAsync job id when async is true or the work is still running.
messageNoHuman-readable error. Never includes stack traces or internal paths.
qualityNoQuality used for this generation.
panel_idNoGenerated or regenerated panel id.
story_idNoCreated or existing story id.
image_urlNoHTTPS URL of the finished panel when async is false and generation succeeded.
next_stepNoWhat the agent should call next. Follow this instead of guessing.
request_idNoRequest correlation id.
credits_chargedNoAPI credits billed for a successful generation.
credits_remainingNoRemaining spendableCredits after the call (apiPack plus purchase-backed packs).

TDQS

A3.8/5.0
Behavior3/5

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

The description adds useful non-schema context: 'Style stays locked,' 'Same Image 1 / Image 2 ref overrides as manga.continue_story,' and 'Costs the same credits as a new panel.' Annotations already signal non-read-only and non-idempotent behavior, so the description supports rather than contradicts them. It does not disclose what happens to the previous panel or whether the operation destroys or replaces anything, which is a notable gap for a regeneration tool.

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 four short sentences, and each one carries meaningful information: the action, stylistic preservation, reference behavior, ID sourcing, and cost. It is front-loaded with the core purpose and contains no fluff or repeated schema content.

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 tool with 12 parameters, 100% schema coverage, an output schema, and annotations, this description is sufficiently complete for an AI to invoke it correctly. It covers purpose, ref override equivalence, ID retrieval, and cost. The main residual gap is that it never explicitly tells the agent when to choose regenerate_panel over create_story or continue_story, but that is more of a routing nicety than a blocking omission.

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 the schema itself thoroughly documents every parameter, including constraints such as 'Do not also send identity_image' and 'Do not also send continuity_panel_id.' The description adds only a mapping hint ('Get ids from manga.list_panels') but does not need to repeat parameter details. Baseline 3 is appropriate because the schema does the heavy lifting

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

Purpose4/5

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

The description uses a specific verb + resource: 'Redraw or edit one panel.' It names the panel as the target and points to manga.list_panels for IDs, distinguishing it from create/continue oriented siblings. It stops short of explicitly contrasting with manga.continue_story or manga.create_story, but the basic purpose is unambiguous.

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 usage context: use this to regenerate or edit an existing panel, and get panel IDs from manga.list_panels. It also references manga.continue_story to explain the Image 1/Image 2 override semantics. It does not explicitly state when not to use it or what alternative to pick for another operation, but the context is strong enough for an agent to select it appropriately.

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 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

A4.4/5.0
Disambiguation5/5

Each tool targets a distinct resource and action: story creation, continuation, regeneration, panel listing, story listing, style listing, credit lookup, credit purchase, and job polling. Even the credit-related tools are clearly separated by purchase versus query. There is no meaningful overlap that would confuse an agent.

Naming Consistency5/5

All tools consistently use the manga. prefix with snake_case verb_noun names like create_story, list_panels, and regenerate_panel. The pattern is uniform across the entire set, making the API predictable and easy to navigate.

Tool Count5/5

Nine tools is a well-scoped size for a manga generation server: three creation-oriented tools, three listing tools, two credit tools, and one async job helper. Each tool serves a clear, non-redundant role in the workflow.

Completeness4/5

The core manga creation lifecycle is well covered: create, continue, regenerate, list stories, and list panels, plus style discovery and credit management. The only notable gaps are destructive operations like deleting stories or panels and perhaps a story detail endpoint, but these are not essential to the primary generation workflow.

Resources