Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@glm-image-mcp-server generate an image of a serene mountain landscape"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Z.AI の glm-image モデルを使用した画像生成 MCP サーバー
MCP サーバー: Claude Desktop やその他の MCP クライアントから画像を生成
バッチ CLI: JSON 設定ファイルから複数の画像を一括生成
自動ダウンロード: 生成された画像は自動的にローカルに保存
Related MCP server: nanobanana-mcp
npm install @dondonudonjp/glm-image-mcp-servergit clone https://github.com/ex-takashima/glm-image-mcp-server.git
cd glm-image-mcp-server
npm install
npm run build変数名 | 必須 | デフォルト値 | 説明 |
| はい | - | Z.AI の API キー |
| いいえ |
| 生成画像の保存先ディレクトリ |
.env.example を参考に .env ファイルを作成してください：
cp .env.example .env
# .env を編集して API キーを設定Claude Desktop の設定ファイル（claude_desktop_config.json）に以下を追加：
{
"mcpServers": {
"glm-image": {
"command": "npx",
"args": ["@dondonudonjp/glm-image-mcp-server"],
"env": {
"Z_AI_API_KEY": "your_api_key"
}
}
}
}ローカルビルドの場合：
{
"mcpServers": {
"glm-image": {
"command": "node",
"args": ["/path/to/glm-image-mcp-server/dist/index.js"],
"env": {
"Z_AI_API_KEY": "your_api_key"
}
}
}
}generate_image
prompt（必須）: 生成する画像の説明テキスト
quality（任意）: "hd"（デフォルト）または "standard"
size_preset（任意）: アスペクト比プリセット（下記参照）
custom_size（任意）: カスタムサイズ（例: "1536x1024"）※事前検証あり
output_filename（任意）: 保存するファイル名
サイズ指定方法:
size_preset と custom_size のどちらかを指定（両方指定時は size_preset 優先）
どちらも未指定の場合は 1:1（1280x1280）がデフォルト
# バッチ処理を実行
npx @dondonudonjp/glm-image-mcp-server/dist/cli.js config.json
# または glm-image-batch コマンド（グローバルインストール時）
glm-image-batch config.json
# JSON 形式で出力
glm-image-batch config.json --format json{
"jobs": [
{
"prompt": "海に沈む美しい夕日",
"quality": "hd",
"size_preset": "16:9",
"output_filename": "sunset.png"
},
{
"prompt": "毛糸で遊ぶ猫",
"custom_size": "1536x1024"
},
{
"prompt": "山の風景"
}
],
"output_directory": "./output",
"concurrency": 3
}0: すべてのジョブが正常に完了
1: 1つ以上のジョブが失敗
# ビルド
npm run build
# ウォッチモード
npm run dev
# MCP インスペクターでテスト
npx @anthropic/mcp-inspector dist/index.jsエンドポイント: POST https://api.z.ai/api/paas/v4/images/generations
モデル: glm-image
品質オプション: hd, standard
サイズプリセット（size_preset）:
プリセット | 解像度 | 用途 |
| 1280x1280 | 正方形（デフォルト） |
| 1568x1056 | 横長写真 |
| 1056x1568 | 縦長写真 |
| 1472x1088 | 横長スタンダード |
| 1088x1472 | 縦長スタンダード |
| 1728x960 | ワイドスクリーン |
| 960x1728 | スマホ縦画面 |
カスタムサイズ（custom_size）の制限:
幅・高さ: 1024px〜2048px
32で割り切れる値のみ
総ピクセル数: 最大 2^22 px（約419万ピクセル）
無効な値を指定した場合、API呼び出し前にエラーを返却
MIT
Generate an image from a text prompt using Z.AI glm-image model
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | The text prompt describing the image to generate | |
| quality | No | Image quality: "hd" (default) or "standard" | |
| custom_size | No | Custom size (e.g., "1536x1024"). Must be 1024-2048px, divisible by 32, max 2^22 total pixels. Ignored if size_preset is specified | |
| size_preset | No | Recommended size preset by aspect ratio. "1:1"=1280x1280 (default), "3:2"=1568x1056, "2:3"=1056x1568, "4:3"=1472x1088, "3:4"=1088x1472, "16:9"=1728x960, "9:16"=960x1728 | |
| output_filename | No | Optional output filename (without path) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the core action and model, with no mention of side effects (e.g., file savings, return format, rate limits, or asynchronous behavior). This leaves significant behavioral ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the essential verb and object. No unnecessary words or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite the schema covering all parameters, there is no output schema, and the description does not explain what the tool returns (e.g., file path, URL, base64) or any side effects like file saving. For a tool with 5 parameters and no return specification, the description should clarify the outcome, but it does not.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all five parameters. The description itself adds no additional parameter meaning beyond what the schema provides, matching the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Generate'), the resource ('an image'), and the source ('from a text prompt using Z.AI glm-image model'). This is specific and leaves no ambiguity about what the tool does, even without sibling comparisons.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for image generation from text, but provides no explicit guidance on when to use this tool versus alternatives, or any prerequisites. With no siblings listed, the implied usage is acceptable but not enhanced.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.1generate_imageThere is only one tool, so there is no possibility of ambiguity or misselection among tools.
With a single tool named 'generate_image', the naming follows a clear verb_noun pattern and is internally consistent.
A single tool is thin for most servers, though it fully covers the stated purpose of image generation. The count feels minimal but not unreasonable.
For the narrow domain of generating an image from a text prompt, the single generate_image tool provides complete coverage without obvious missing operations.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for Qwen Image 3 AI image generation
MCP server for GLM chat completions using Zhipu AI models via AceDataCloud
MCP server for Hailuo (MiniMax) AI video generation
MCP server for Flux AI image generation
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ex-takashima/glm-image-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server