AI & Machine Learning

mangii.ai

Provides API endpoints for creating and managing AI-generated manga stories, panels, and art styles.

1 endpoint9 known toolsFirst detected August 23, 2026Last detected August 26, 2026

ENDPOINT 1

https://mcp.mangii.ai/mcp

No auth detected

MCP server metadata

Name: mangii-mcp
Version: 1.4.0

Capabilities

toolspromptsresourcescompletions

Server instructions

Mangii generates manga, anime, webtoon, and manhwa panels from plain-language prompts. Creation flow: 1) manga.list_styles (or read resource manga://styles) 2) manga.create_story with style_id and async=false 3) keep story_id and panel_id 4) manga.continue_story for later panels (never send style_id). If you lost story_id, call manga.list_stories. Refs: continue defaults Image 1 = first panel (identity) and Image 2 = last distinct panel (scene). Get ids from create/continue results or manga.list_panels (ref_role identity/scene). Override Image 1 with identity_panel_id or identity_image (https URL or data URI; reference_image is an alias). Override Image 2 with continuity_panel_id or continuity_image. Do not send a panel id and an image for the same slot. Redraw one panel with manga.regenerate_panel (same ref overrides). If you set async=true, poll manga.get_job until status=succeeded. On manga.create_story, manga.continue_story, and manga.regenerate_panel, send idempotency_key (8-200 chars) and reuse it on retry so a timeout does not charge twice. Read manga://guide for the full flow. Use prompt manga.create or manga.continue as slash-command templates. Quality costs spendableCredits (apiPack + purchase-backed packs): standard 1, hd 2, ultra 5. Failed generations refund. On 402 call manga.buy_credits. Mint a key at https://mangii.ai/console/keys.

Known tools 9

manga.list_styles

List the 24 canonical Mangii art styles with live style ids.

Inferred read-only

manga.get_credits

Return the API wallet.

Inferred read-only

manga.list_panels

List panels you own for a story.

Inferred read-only

manga.list_stories

List stories you own, newest first.

Inferred read-only

manga.create_story

Start a new private manga (panel 1).

Inferred read-only

manga.continue_story

Add the next panel.

Inferred read-only

manga.regenerate_panel

Redraw or edit one panel.

Potential side effects

manga.buy_credits

Return the Console billing URL so a human can fund apiPackCredits.

Inferred read-only

manga.get_job

Poll a generation job from manga.create_story, manga.continue_story, or manga.regenerate_panel when async=true.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.mangii-mcp]
url = "https://mcp.mangii.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "mangii-mcp": {
      "type": "http",
      "url": "https://mcp.mangii.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: mangii-mcp
Remote MCP URL: https://mcp.mangii.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "mangii-mcp": {
      "url": "https://mcp.mangii.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "mangii-mcp": {
      "type": "http",
      "url": "https://mcp.mangii.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "mangii-mcp",
  "transport": "streamable-http",
  "url": "https://mcp.mangii.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for mangii.ai was fetched 2026-08-25T18:21:38.860Z.

Trust status Trusted

mangii.ai is assessed as Trusted: Domain runs a meaningful technology spend, consistent with a real business.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.