Midjourney Best Experience MCP Server
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., "@Midjourney Best Experience MCP Server Generate a futuristic cyberpunk city at sunset --ar 16:9"
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.
Midjourney Best Experience MCP Server
用于访问 Midjourney Best Experience API 的 MCP 服务器。
🚀 使用 EMCP 平台快速体验
EMCP 是一个强大的 MCP 服务器管理平台,让您无需手动配置即可快速使用各种 MCP 服务器!
快速开始:
🌐 访问 EMCP 平台
📝 注册并登录账号
🎯 进入 MCP 广场,浏览所有可用的 MCP 服务器
🔍 搜索或找到本服务器(
bach-midjourney_best_experience)🎉 点击 "安装 MCP" 按钮
✅ 完成!即可在您的应用中使用
EMCP 平台优势:
✨ 零配置:无需手动编辑配置文件
🎨 可视化管理:图形界面轻松管理所有 MCP 服务器
🔐 安全可靠:统一管理 API 密钥和认证信息
🚀 一键安装:MCP 广场提供丰富的服务器选择
📊 使用统计:实时查看服务调用情况
立即访问 EMCP 平台 开始您的 MCP 之旅!
Related MCP server: openai-gpt-image-mcp
简介
这是一个 MCP 服务器,用于访问 Midjourney Best Experience API。
PyPI 包名:
bach-midjourney_best_experience版本: 1.0.0
传输协议: stdio
安装
从 PyPI 安装:
pip install bach-midjourney_best_experience从源码安装:
pip install -e .运行
方式 1: 使用 uvx(推荐,无需安装)
# 运行(uvx 会自动安装并运行)
uvx --from bach-midjourney_best_experience bach_midjourney_best_experience
# 或指定版本
uvx --from bach-midjourney_best_experience@latest bach_midjourney_best_experience方式 2: 直接运行(开发模式)
python server.py方式 3: 安装后作为命令运行
# 安装
pip install bach-midjourney_best_experience
# 运行(命令名使用下划线)
bach_midjourney_best_experience配置
API 认证
此 API 需要认证。请设置环境变量:
export API_KEY="your_api_key_here"环境变量
变量名 | 说明 | 必需 |
| API 密钥 | 是 |
| 不适用 | 否 |
| 不适用 | 否 |
在 Cursor 中使用
编辑 Cursor MCP 配置文件 ~/.cursor/mcp.json:
{
"mcpServers": {
"bach-midjourney_best_experience": {
"command": "uvx",
"args": ["--from", "bach-midjourney_best_experience", "bach_midjourney_best_experience"],
"env": {
"API_KEY": "your_api_key_here"
}
}
}
}在 Claude Desktop 中使用
编辑 Claude Desktop 配置文件 claude_desktop_config.json:
{
"mcpServers": {
"bach-midjourney_best_experience": {
"command": "uvx",
"args": ["--from", "bach-midjourney_best_experience", "bach_midjourney_best_experience"],
"env": {
"API_KEY": "your_api_key_here"
}
}
}
}可用工具
此服务器提供以下工具:
action_relaxuu0026v
Do the relax action - You can perform upsample (same as the UI, U2...), variation (V1, V2...), zoom out 1.5x, zoom out 2x, pan, and other operations on the images generated in the first step
端点: POST /mj/action-relax
参数:
action(string) 必需: the action is the enumeration values returned in the action list in the callbackimage_id(string) 必需: the params image_id in the relax job callback or task_id eg: 9c4410a2-2bb4-2428-b0e4-0a3b41f48e3bhook_url(string): if set will notify the result to your hook_url
action_fastuu0026v
Do the fast action - You can perform upsample (same as the UI, U2...), variation (V1, V2...), zoom out 1.5x, zoom out 2x, pan, and other operations on the images generated in the first step
端点: POST /mj/action-fast
参数:
action(string) 必需: the action is the enumeration values returned in the action list in the callbackimage_id(string) 必需: the params image_id in the fast job callback or task_id eg: 6a028074-884e-7840-2ef4-715a5ab3b6c7hook_url(string): Example value: https://www.google.com
generate_relax
generate the images relax Generate queue asynchronous notifications to hook_ url, overall generation time is Depends on account status and task queuing
端点: POST /mj/generate-relax
参数:
prompt(string) 必需: Example value: a beautiful cat --ar 1920:1080hook_url(string): if set will notify the result to your hook_url
generate_fast
generate the images fast Generate queue asynchronous notifications to hook_ url, overall generation time is around 40-60s
端点: POST /mj/generate-fast
参数:
prompt(string) 必需: Example value: a beautiful cat --ar 1920:1080hook_url(string): if set will notify the result to your hook_url
get_job_by_task_id
you can get the generate job and action job status by the task_id, and the task_id will expired at 24 hours after
端点: GET /mj/get-task-id
参数:
task_id(string) 必需: Example value: 6ddd8121-2ae4-af61-b73d-eaefc8318d09
技术栈
传输协议: stdio
HTTP 客户端: httpx
许可证
MIT License - 详见 LICENSE 文件。
开发
此服务器由 API-to-MCP 工具生成。
版本: 1.0.0
Available Tools
5 toolsaction_fastuu0026vC
Do the fast action - You can perform upsample (same as the UI, U2...), variation (V1, V2...), zoom out 1.5x, zoom out 2x, pan, and other operations on the images generated in the first step
Inputs: action (required), image_id (required), hook_url.
action_relaxuu0026vC
Do the relax action - You can perform upsample (same as the UI, U2...), variation (V1, V2...), zoom out 1.5x, zoom out 2x, pan, and other operations on the images generated in the first step
Inputs: action (required), image_id (required), hook_url.
generate_fastC
generate the images fast Generate queue asynchronous notifications to hook_ url, overall generation time is around 40-60s
Inputs: prompt (required), hook_url.
generate_relaxC
generate the images relax Generate queue asynchronous notifications to hook_ url, overall generation time is Depends on account status and task queuing
Inputs: prompt (required), hook_url.
get_job_by_task_idB
you can get the generate job and action job status by the task_id, and the task_id will expired at 24 hours after
Inputs: task_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Tools are mostly distinct by mode (fast vs relax) and purpose (generate vs action vs status), but the 'action_fastuu0026v' and 'action_relaxuu0026v' have confusing suffixes that could cause ambiguity.
Naming pattern is inconsistent: 'generate_fast' and 'generate_relax' use underscore, while 'action_fastuu0026v' and 'action_relaxuu0026v' append a cryptic suffix. 'get_job_by_task_id' follows a different verb_noun pattern.
With 5 tools, the server is well-scoped for its purpose of image generation and manipulation. Each tool covers a distinct aspect: fast/relax generation, corresponding actions, and status checking.
The set covers the core workflow: generate (fast/relax), apply actions (upsample, variation, zoom), and check status. A minor gap is the lack of a tool to directly retrieve the generated image URL, but status likely provides this.
Maintenance
Related MCP Connectors
MCP server for Midjourney AI image generation and editing
MCP server for Qwen Image 3 AI image generation
MCP server for Flux AI image generation
MCP server for Google Veo AI video generation
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA complete Midjourney MCP server that provides image generation features through the GPTNB API, including text-to-image generation, image transformations, advanced editing, and face swapping capabilities.12-
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables image generation and editing using OpenAI's DALL-E models with support for text prompts, inpainting, and outpainting. It includes advanced features like automatic aspect ratio mapping and intelligent file management to handle large image payloads.90 npm1MIT
- AlicenseAqualityDmaintenanceAn MCP server that provides AI image generation and editing capabilities using Google's Gemini 2.5 Flash Image API. It allows users to create new images from text, modify existing files, and perform iterative edits through natural language prompts.61,729 npmMIT
- AlicenseBqualityDmaintenanceUnofficial MCP server for generating images via Midjourney web app using authentication cookies. Enables text-to-image generation with customizable parameters.11GPL 3.0