AI 画像生成のために Amazon Bedrock の Nova Canvas モデルと統合するモデル制御プロトコル (MCP) サーバー。
AmazonのNova Canvasモデルを使用したテキスト説明からの高品質画像生成
ネガティブプロンプトによる高度な制御で画像構成を洗練
画像のサイズと品質を柔軟に設定できるオプション
シード制御による決定論的な画像生成
堅牢な入力検証とエラー処理
Related MCP server: AWS Nova Canvas
Amazon Bedrock および Nova Canvas モデルへのアクセスが可能なアクティブな AWS アカウント
必要な権限を持つAWS認証情報が適切に設定されている
Node.js バージョン 18 以降
サーバーには、適切な Amazon Bedrock 権限を持つ AWS 認証情報が必要です。以下のいずれかの方法で設定してください。
環境変数:
export AWS_ACCESS_KEY_ID=your_access_key
export AWS_SECRET_ACCESS_KEY=your_secret_key
export AWS_REGION=us-east-1 # or your preferred regionAWS 認証情報ファイル ( ~/.aws/credentials ):
[the_profile_name]
aws_access_key_id = your_access_key
aws_secret_access_key = your_secret_keyアクティブプロファイルの環境変数:
export AWS_PROFILE=the_profile_nameIAM ロール (AWS インフラストラクチャにデプロイされている場合)
Claude Desktop と統合するには、設定ファイルに次の構成を追加します。
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"amazon-bedrock": {
"command": "npx",
"args": [
"-y",
"@zxkane/mcp-server-amazon-bedrock"
],
"env": {
"AWS_PROFILE": "your_profile_name", // Optional, only if you want to use a specific profile
"AWS_ACCESS_KEY_ID": "your_access_key", // Optional if using AWS credentials file or IAM role
"AWS_SECRET_ACCESS_KEY": "your_secret_key", // Optional if using AWS credentials file or IAM role
"AWS_REGION": "us-east-1" // Optional, defaults to 'us-east-1'
}
}
}
}Amazon Bedrock の Nova Canvas モデルを使用して、テキストの説明から画像を作成します。
prompt （必須）: 希望する画像の説明文（1～1024文字）
negativePrompt （オプション）：画像から除外する要素（1〜1024文字）
width （オプション）：ピクセル単位の画像の幅（デフォルト：1024）
height （オプション）：ピクセル単位の画像の高さ（デフォルト：1024）
quality （オプション）：画像品質レベル - 「標準」または「プレミアム」（デフォルト：「標準」）
cfg_scale （オプション）：プロンプト遵守強度（1.1-10、デフォルト：6.5）
seed （オプション）：再現性のための生成シード（0-858993459、デフォルト：12）
numberOfImages (オプション): 生成のバッチサイズ (1-5、デフォルト: 1)
const result = await callTool('generate_image', {
prompt: "A serene mountain landscape at sunset",
negativePrompt: "people, buildings, vehicles",
quality: "premium",
cfg_scale: 8,
numberOfImages: 2
});最適な結果を得るには、メインプロンプトで否定的な表現（「いいえ」「ない」「なし」など）を避けてください。代わりに、これらの要素をnegativePromptパラメータに移動してください。例えば、プロンプトで「建物のない風景」を使用する代わりに、 negativePromptでは「建物」を使用してください。
詳細な使用ガイドラインについては、 Nova Canvas のドキュメントを参照してください。
ローカル環境でサーバーをセットアップして実行するには:
git clone https://github.com/zxkane/mcp-server-amazon-bedrock.git
cd mcp-server-amazon-bedrock
npm install
npm run build生成時間は、解像度（ widthとheight ）、 numberOfImages 、およびquality設定によって影響を受けます。高い値を使用する場合は、実装においてタイムアウトが発生する可能性があることにご注意ください。
このプロジェクトは MIT ライセンスに基づいてライセンスされています - 詳細については LICENSE ファイルを参照してください。
Generate image(s) using Amazon Nova Canvas model. The returned data is Base64-encoded string that represent each image that was generated.
| Name | Required | Description | Default |
|---|---|---|---|
| cfg_scale | No | How closely to follow the prompt (1.1-10, default: 6.5) | |
| height | No | Height of the generated image (default: 1024) | |
| negativePrompt | No | Optional text description of what to avoid in the image (1-1024 characters) | |
| numberOfImages | No | Number of images to generate (1-5, default: 1) | |
| prompt | Yes | Text description of the image to generate (1-1024 characters) | |
| quality | No | Quality of the generated image (default: standard) | |
| seed | No | Seed for reproducible generation (0-858993459, default: 12) | |
| width | No | Width of the generated image (default: 1024) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the return format (Base64-encoded string) but lacks critical details such as rate limits, authentication requirements, error handling, or whether this is a read/write operation. For a complex image generation tool, this is insufficient.
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 concise and front-loaded, consisting of two clear sentences. However, it could be slightly more efficient by combining ideas, but it avoids unnecessary verbosity.
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?
Given the complexity of an image generation tool with 8 parameters and no output schema or annotations, the description is incomplete. It covers the basic purpose and return format but misses behavioral context, usage guidelines, and output details, leaving significant gaps for an AI agent.
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 fully documents all 8 parameters. The description adds no parameter-specific information beyond what's in the schema, resulting in a baseline score of 3.
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 tool's purpose: 'Generate image(s) using Amazon Nova Canvas model.' It specifies the verb ('generate') and resource ('image(s)'), and identifies the specific model. However, without sibling tools, we cannot assess differentiation, so it cannot achieve a perfect 5.
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 provides no guidance on when to use this tool versus alternatives, prerequisites, or typical use cases. It simply states what the tool does without context for selection.
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.
v1.0.0generate_imageScored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The tool 'generate_image' has a clear and distinct purpose that cannot be mistaken for any other tool in the set.
The single tool name 'generate_image' follows a verb_noun pattern, and with only one tool, consistency is inherently perfect. There are no other tools to compare against, so no inconsistencies can arise.
A single tool is too few for a server named 'Amazon Bedrock MCP Server', which suggests a broader scope related to Amazon Bedrock services. This minimal toolset feels thin and incomplete for the implied domain, limiting functionality to just image generation.
The tool surface is severely incomplete for the server's purpose. Amazon Bedrock includes multiple models and capabilities beyond image generation, such as text generation, embeddings, and model management. The single tool fails to cover these core aspects, leaving significant gaps that will cause agent failures.
Create images and videos from prompts, with options for image mixing, reference images, and start/…
Generate AI images and videos from any compatible MCP client.
Generate and edit images, create videos, quote credit costs, and retrieve private results.
Create AI images and videos, manage projects and credits, and use workspace campaign context.
