一个集成了 4o-image API 的 MCP 服务器实现，使 LLM 和其他 AI 系统能够通过标准化协议生成和编辑图像。使用简单的文本提示即可创建高质量的艺术作品、3D 角色和自定义图像。
文本到图像生成：利用人工智能从文本描述创建图像
图像编辑：使用文本提示转换现有图像
实时进度更新：获取生成状态的反馈
浏览器集成：在默认浏览器中自动打开生成的图像
Related MCP server: image-forge-mcp
生成图像
根据文本提示生成图像，并可选择进行图像编辑
输入：
prompt （字符串，必需）：所需图像的文本描述
imageBase64 （字符串，可选）：用于编辑或样式转换的 Base64 编码图像
在4o-image.app注册一个账户
从用户仪表板获取您的 API 密钥
运行服务器时将 API 密钥设置为环境变量
将其添加到您的claude_desktop_config.json中：
{
"mcpServers": {
"4o-image": {
"command": "npx",
"args": [
"-y",
"4oimage-mcp"
],
"env": {
"API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}以下是将此 MCP 服务器与 Claude 一起使用的示例：
Generate an image of a dog running on the beach at sunsetClaude 将使用 MCP 服务器生成图片，该图片将自动在您的默认浏览器中打开。您还会在 Claude 的回复中获得该图片的直接链接。
对于图像编辑，您可以包含一个基础图像并提示 Claude 对其进行修改：
Edit this image to make the sky more dramatic with storm clouds此 MCP 服务器遵循 MIT 许可证。您可以自由使用、修改和分发该软件，但须遵守 MIT 许可证的条款和条件。
Generate images using the 4o-image API and automatically open the results in your browser.
This tool generates images based on your prompt and automatically opens them in your default browser, while also returning a clickable link.
The tool supports two modes:
Text-to-image - Create new images using just a text prompt
Image editing - Provide a base image and prompt for editing or style transfer
The response will include a direct link to the generated image and detailed information.
Visit our website: https://4o-image.app/
| Name | Required | Description | Default |
|---|---|---|---|
| imageBase64 | No | Optional base image (Base64 encoded) for image editing or upscaling | |
| prompt | Yes | Text description of the desired image content |
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 adds valuable context beyond the input schema by describing automatic browser opening, return of a clickable link, and support for two modes. However, it does not cover important behavioral traits such as rate limits, authentication needs, error handling, or response format details, leaving gaps for a mutation tool.
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 well-structured and front-loaded, starting with the core functionality and then detailing modes and responses. Most sentences add value, but the final promotional sentence ('Visit our website...') is extraneous and does not aid tool selection or invocation, slightly reducing efficiency.
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 tool's complexity (image generation with two modes), no annotations, and no output schema, the description is moderately complete. It covers purpose, usage modes, and some behavioral aspects (browser opening, link return), but lacks details on output structure, error cases, or operational constraints, which are important for a tool without structured output documentation.
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 input schema already documents both parameters (imageBase64 and prompt) adequately. The description adds marginal value by explaining the two modes that correspond to these parameters, but it does not provide additional syntax, format, or constraint details beyond what the schema states. This meets the baseline for high schema coverage.
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 images using the 4o-image API' and specifies it 'automatically opens the results in your browser.' It distinguishes between text-to-image and image editing modes, providing specific functionality details. However, without sibling tools, differentiation from alternatives is not applicable, preventing a perfect score.
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 clear usage context by outlining two modes (text-to-image and image editing) and indicating when to use each based on whether an imageBase64 parameter is provided. It mentions that the tool opens results in the browser and returns a clickable link, offering practical guidance. However, it lacks explicit exclusions or comparisons to alternatives, as no sibling tools exist.
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.
v1.0.0generateImageScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'generateImage' has a clear, distinct purpose for image generation and editing.
The tool name 'generateImage' follows a consistent verb_noun pattern, and with only one tool, there is no inconsistency to evaluate. The naming is clear and appropriate for its function.
A single tool is too few for the server's purpose of image generation and editing, as it lacks coverage for related operations like listing generated images, managing settings, or handling errors. This minimal set limits agent functionality and feels incomplete for the domain.
The tool surface is severely incomplete for an image generation server. While 'generateImage' covers creation and editing, there are obvious gaps such as no tools for retrieving past images, deleting images, or configuring generation parameters, which are essential for a full workflow.
MCP server for Qwen Image 3 AI image generation
Generate AI images and videos from any compatible MCP client.
Generate game-ready 3D models, textures, and audio from natural language, over MCP.
MCP server for Hailuo (MiniMax) AI video generation