MCP.so
ログイン

Gelbooru MCP Server

@citronlegacy

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

citronlegacy

投稿者

Citron Legacy

Gelbooru MCP Server について

A Python MCP server that wraps the Gelbooru API. Connect it to any MCP-compatible client (Claude Desktop, Cursor, etc.) to search posts, look up tags, and generate Stable Diffusion prompts from real character appearance data — all directly from your AI assistant.

Gelbooru MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "gelbooru-mcp": {
      "command": "/absolute/path/to/.venv/bin/python",
      "args": [
        "/absolute/path/to/gelbooru_mcp.py"
      ],
      "env": {
        "GELBOORU_API_KEY": "your_api_key",
        "GELBOORU_USER_ID": "your_user_id"
      }
    }
  }
}

Gelbooru MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Gelbooru Mcp?

A Python MCP server that wraps the Gelbooru API. Connect it to any MCP-compatible client (Claude Desktop, Cursor, etc.) to search posts, look up tags, and generate Stable Diffusion prompts from real character appearance data — all directly from your AI assistant.

How to use Gelbooru Mcp?

Clone the repository, run install.sh (or install mcp manually with pip), then set the optional environment variables GELBOORU_API_KEY and GELBOORU_USER_ID. Start the server with python gelbooru_mcp.py and configure your MCP client (e.g., Claude Desktop) to run the script via the stdio transport.

Key features of Gelbooru Mcp

  • Stable Diffusion Prompt Generation – Build accurate SD prompts from tag frequency data.
  • Appearance Breakdown – Separate eye, hair, and clothing tags with frequency counts.
  • Advanced Post Search – Filter by tags, score, resolution, rating, uploader, and more.
  • Full Tag Syntax – Supports AND, OR, wildcards, exclusion, meta-tags, and sorting.
  • Community Tools – Search users, get post comments, and list deleted posts.
  • Smart Caching – Results cached for 24 hours to avoid repeated API calls.

Use cases of Gelbooru Mcp

  • Generate a Stable Diffusion prompt for a character by analyzing their most-tagged posts.
  • Find high-quality wallpaper images using score, width, and tag filters.
  • Check how many posts a specific tag has and discover related tags.
  • Retrieve comments on a given post or track recently deleted content.

よくある質問

1

Do I need a Gelbooru API key?

API credentials are optional but strongly recommended. Without them, requests are throttled and limited to 2 tags per query. Patreon supporters of Gelbooru receive unlimited requests.

2

What are the runtime requirements?

Python 3.10+ and the `mcp` package. The server uses the stdio transport and does not require a web server.

3

How are Stable Diffusion prompts generated?

The server fetches the most-tagged `rating:general solo` posts for a character, analyzes tag frequency across eye, hair, and other categories, then assembles a ready-to-paste prompt string. Results are cached for 24 hours by default.

4

What tag format does Gelbooru use?

Gelbooru uses `character_(series)` format with underscores (e.g., `misty_(pokemon)`). Always convert natural language names to this format before using the tools. Use `search_tags` with `name_pattern` if unsure.

コメント

「AI とエージェント」の他のコンテンツ