Click on "Deploy 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., "@Gentou Generate an image of a cat wearing a hat"
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.
このリポジトリはYOROZUで作成されましたhttps://github.com/Sunwood-ai-labs/YOROZU
fal-mcp-server-gentou は、Fal AI の強力な画像生成モデル（fal-ai/nano-banana-pro）を Model Context Protocol (MCP) を通じて利用可能にするサーバーです。
これにより、Claude desktop やその他の MCP クライアントから直接、高品質な画像を生成することができます。
Related MCP server: Nano Banana MCP Server
高速生成: fal-ai/nano-banana-pro モデルを使用し、数秒で画像を生成します。
シンプルなインターフェース: プロンプトを入力するだけで、直感的に操作可能。
柔軟な設定: アスペクト比や画像数、フォーマットをカスタマイズ可能。
すぐにサーバーを起動したい場合は、npx を使用するのが最も簡単です。
npx -y @sunwood-ai-labs/fal-mcp-server-gentou頻繁に使用する場合は、グローバルにインストールすることをお勧めします。
npm install -g @sunwood-ai-labs/fal-mcp-server-gentou
# 実行 (Run)
@sunwood-ai-labs/fal-mcp-server-gentou開発に参加する場合や、ソースコードからビルドしたい場合の手順です。
git clone https://github.com/Sunwood-ai-labs/fal-mcp-server-gentou.git
cd fal-mcp-server-gentou
npm install
npm run build.env ファイルを作成し、Fal AI の API キーを設定してください。
FAL_KEY=your_fal_key_hereMCP 設定ファイル（例: claude_desktop_config.json）に以下を追加します。
{
"mcpServers": {
"gentou": {
"command": "npx",
"args": ["-y", "@sunwood-ai-labs/fal-mcp-server-gentou"],
"env": {
"FAL_KEY": "your_fal_key_here"
}
}
}
}{
"mcpServers": {
"gentou": {
"command": "node",
"args": ["/absolute/path/to/fal-mcp-server-gentou/dist/index.js"],
"env": {
"FAL_KEY": "your_fal_key_here"
}
}
}
}generate_image画像を生成します。
prompt (required): 画像の説明
aspect_ratio: アスペクト比 (デフォルト: "1:1")
num_images: 生成枚数 (デフォルト: 1)
output_format: 出力フォーマット (デフォルト: "png")
ISC
Fal AI (fal-ai/nano-banana-pro) を使用して画像を生成します。
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | 生成する画像のプロンプト (英語推奨) | |
| num_images | No | 生成する画像の枚数 | |
| aspect_ratio | No | アスペクト比 (例: '1:1', '16:9') | 1:1 |
| output_format | No | 出力フォーマット (例: 'png', 'jpeg') | png |
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 reveals that generation happens through an external provider (Fal AI) and names the model, which is genuine added context, but it says nothing about latency, cost, rate limits, or failure modes for what is clearly a remote generation call.
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?
A single short, front-loaded sentence with no filler. It is efficient, though the extreme brevity borders on under-specification for a generative tool rather than being a model of well-structured conciseness.
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?
There is no output schema, no annotations, and four parameters, yet the description never states what the tool returns (image URL, base64, file reference) or where results land. For a tool with zero structured behavioral coverage, this leaves a significant gap an agent would need in order to use the result.
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 all four parameters (prompt, num_images, aspect_ratio, output_format) are already documented in the schema, including defaults and examples. The description adds nothing beyond that, making the baseline 3 appropriate.
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 names a specific verb (生成します) and resource (画像) and even identifies the backing model/provider (fal-ai/nano-banana-pro), so the agent knows exactly what the tool does. There are no sibling tools to differentiate from, so the only missing element is the differentiation clause that a 5 would require.
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 gives no guidance on when to use this tool versus alternatives, no prerequisites, and no indication of when it would be inappropriate (e.g., cost, latency, external API dependency). It states only what the tool does, leaving all usage context to inference.
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
There is only a single tool, generate_image, so there is no possibility of confusing it with another. Its purpose is unambiguous and clearly communicated.
The sole tool follows a clean verb_noun convention (generate_image). With only one name there is no inconsistency, though the pattern is trivially consistent.
A single tool is on the thin side for a server, even one focused narrowly on image generation. It works but leaves little surface for an agent to compose workflows with.
Generation is covered, but there are no companion operations such as edit, upscale, variation, or status/retrieval of prior generations. For the narrow generation purpose it is adequate, but the surface has obvious dead ends.
MCP server for NanoBanana AI image generation and editing
MCP server for Qwen Image 3 AI image generation
MCP server for Flux AI image generation
MCP server for Grok Imagine AI video generation