Skip to main content
Glama
enesjakozh
GongRzhe

Image Generation MCP Server

by GongRzhe
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

画像生成MCPサーバー

この MCP サーバーは、Replicate Flux モデルを使用したイメージ生成機能を提供します。

インストール

オプション 1: NPX 方式 (ローカル セットアップは不要)

ローカルにインストールせずに、npm から直接パッケージを使用できます。

# No installation needed - npx will handle it

オプション2: ローカルインストール

ローカルインストールを希望する場合:

# Global installation
npm install -g @gongrzhe/image-gen-server

# Or local installation
npm install @gongrzhe/image-gen-server

Related MCP server: FLUX MCP Server

設定

Claudeデスクトップの設定

Claude Desktop 構成ファイルを編集します。

  • MacOSの場合: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows の場合: %APPDATA%/Claude/claude_desktop_config.json

オプション 1: NPX 構成 (推奨)

この方法では、ローカル ファイルを必要とせずに npm から直接サーバーを実行します。

{
  "mcpServers": {
    "image-gen": {
      "command": "npx",
      "args": ["@gongrzhe/image-gen-server"],
      "env": {
        "REPLICATE_API_TOKEN": "your-replicate-api-token",
        "MODEL": "alternative-model-name"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

オプション2: ローカルインストール構成

パッケージをローカルにインストールした場合:

{
  "mcpServers": {
    "image-gen": {
      "command": "node",
      "args": ["/path/to/image-gen-server/build/index.js"],
      "env": {
        "REPLICATE_API_TOKEN": "your-replicate-api-token",
        "MODEL": "alternative-model-name"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

複製APIトークンを取得する

  1. https://replicate.comでサインアップ/ログインしてください

  2. https://replicate.com/account/api-tokensにアクセスしてください。

  3. 新しいAPIトークンを作成する

  4. トークンをコピーし、MCP設定でyour-replicate-api-tokenを置き換えます。

画像

環境変数

  • REPLICATE_API_TOKEN (必須): 認証用のReplicate APIトークン

  • MODEL （オプション）: 画像生成に使用するReplicateモデル。デフォルトは「black-forest-labs/flux-schnell」

構成パラメータ

  • disabled : サーバーが有効 ( false ) か無効 ( true ) かを制御します

  • autoApprove : ユーザーの確認なしで実行できるツール名の配列。配列が空の場合、すべてのツール呼び出しは確認が必要になります。

利用可能なツール

画像を生成する

テキストプロンプトに基づいて Flux モデルを使用して画像を生成します。

画像

アウト0（1）

パラメータ

  • prompt （必須）: 生成する画像のテキスト説明

  • seed （オプション）：再現可能な生成のためのランダムシード

  • aspect_ratio (オプション): 画像のアスペクト比 (デフォルト: "1:1")

  • output_format (オプション): 出力形式 - "webp"、"jpg"、または "png" (デフォルト: "webp")

  • num_outputs (オプション): 生成する画像の数 (1-4、デフォルト: 1)

使用例

const result = await use_mcp_tool({
  server_name: "image-gen",
  tool_name: "generate_image",
  arguments: {
    prompt: "A beautiful sunset over mountains",
    aspect_ratio: "16:9",
    output_format: "png",
    num_outputs: 1
  }
});

このツールは、生成された画像への URL の配列を返します。

📜 ライセンス

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。

Available Tools

1 tool
generate_imageC

Generate an image using the Flux model

NameRequiredDescriptionDefault
promptYesPrompt for generated image
seedNoRandom seed for reproducible generation
aspect_ratioNoAspect ratio for the generated image1:1
output_formatNoFormat of the output imageswebp
num_outputsNoNumber of outputs to generate (1-4)

TDQS

C2.9/5.0
Behavior2/5

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 states the action ('generate') but doesn't mention cost, rate limits, permissions, or output behavior (e.g., file format, size). This is a significant gap for a generative tool with potential resource implications.

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 a single, efficient sentence with zero waste. It's front-loaded with the core action and model, making it easy to parse quickly. Every word earns its place without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of image generation, no annotations, and no output schema, the description is incomplete. It doesn't cover behavioral aspects like cost, rate limits, or output details (e.g., image size, quality), leaving gaps for the agent to operate effectively.

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 fully documents all parameters. The description adds no additional meaning beyond the schema, such as explaining prompt best practices or seed usage. Baseline 3 is appropriate when 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 clearly states the verb ('generate') and resource ('image'), specifying the model ('Flux model'). It's specific about what the tool does, though without sibling tools, differentiation isn't applicable. It's not tautological or misleading.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, prerequisites, or constraints. The description lacks context for usage, such as when image generation is appropriate or any limitations, leaving the agent without operational guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.1
    • First observedgenerate_image
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear and distinct purpose of generating images using the Flux model.

Naming Consistency5/5

Since there is only one tool, naming consistency is inherently perfect. The tool name 'generate_image' follows a clear verb_noun pattern, and there are no other tools to cause inconsistency.

Tool Count2/5

A single tool for an image generation server is too few for the apparent scope, as it lacks basic operations like listing models, managing generations, or handling variations. This minimal set will likely cause agent failures due to incomplete functionality.

Completeness1/5

The tool surface is severely incomplete for an image generation domain. It only provides generation without any supporting operations such as model selection, parameter tuning, history retrieval, or image editing, leading to dead ends in agent workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches