midjourney-mcp-web
Unofficial MCP server for generating images via Midjourney web app using authentication cookies. Enables text-to-image generation with customizable parameters.
README
Midjourney MCP Web
Unofficial Model Context Protocol (MCP) server for generating images through the Midjourney web app using your own signed-in browser authentication cookies.
This project is a cleaned-up and modernized fork of Lala-0x3f/mj-mcp. It keeps the same simple MCP surface, but updates the web flow for the current Midjourney site:
- submits jobs to
/api/submit-jobs - reads the Midjourney user id from the signed-in web page
- polls
/api/imagineinstead of relying on the now-blocked websocket path - defaults to
--v 8.1
This project is not affiliated with, endorsed by, or supported by Midjourney.
Tool
The server exposes one MCP tool:
generating_image(prompt: str, aspect_ratio: str) -> str
The response is Markdown with four Midjourney CDN image URLs.
Requirements
- Python 3.10+
uvor another Python package runner- A Midjourney account with access to the web app
- Your own
__Host-Midjourney.AuthUserTokenV3_rand__Host-Midjourney.AuthUserTokenV3_icookie values
Install From GitHub
uvx --from git+https://github.com/WilliamJizh/midjourney-mcp-web midjourney-mcp-web
For local development:
git clone https://github.com/WilliamJizh/midjourney-mcp-web.git
cd midjourney-mcp-web
uv run --with-editable . python -m midjourney_mcp_web
Configuration
The server reads configuration from environment variables.
| Variable | Required | Default | Description |
|---|---|---|---|
TOKEN_R |
Yes | Value of __Host-Midjourney.AuthUserTokenV3_r |
|
TOKEN_I |
Yes | Value of __Host-Midjourney.AuthUserTokenV3_i |
|
API_BASE |
No | www.midjourney.com |
Midjourney web host |
SUFFIX |
No | --v 8.1 |
Parameters appended to every prompt |
MJ_JOB_TIMEOUT_SEC |
No | 300 |
Polling timeout for completed job visibility |
CHANNEL_ID |
No | singleplayer_<user_id> |
Override channel id |
Never commit real token values. Treat both tokens as secrets.
Codex Config Example
[mcp_servers.midjourney]
command = "uvx"
args = ["--from", "git+https://github.com/WilliamJizh/midjourney-mcp-web", "midjourney-mcp-web"]
[mcp_servers.midjourney.env]
TOKEN_R = "replace_with_midjourney_cookie_r"
TOKEN_I = "replace_with_midjourney_cookie_i"
SUFFIX = "--v 8.1"
For better local security on macOS, store the tokens in Keychain and use a small wrapper script that exports TOKEN_R and TOKEN_I before launching this server. Do not publish that wrapper with real values.
Claude Desktop Config Example
{
"mcpServers": {
"midjourney": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/WilliamJizh/midjourney-mcp-web",
"midjourney-mcp-web"
],
"env": {
"TOKEN_R": "replace_with_midjourney_cookie_r",
"TOKEN_I": "replace_with_midjourney_cookie_i",
"SUFFIX": "--v 8.1"
}
}
}
}
Getting Cookie Values
- Open
https://www.midjourney.com/explore?tab=topwhile signed in. - Open browser developer tools.
- Go to Application or Storage.
- Open Cookies for
https://www.midjourney.com. - Copy the values for:
__Host-Midjourney.AuthUserTokenV3_r__Host-Midjourney.AuthUserTokenV3_i
Do not paste these values into public chats, issues, logs, or commits.
Example Prompt
A peaceful impressionist garden with water lilies and soft morning light --stylize 200
Call the MCP tool with:
{
"prompt": "A peaceful impressionist garden with water lilies and soft morning light --stylize 200",
"aspect_ratio": "3:4"
}
The server appends:
--ar 3:4 --v 8.1
unless you override SUFFIX.
Development
uv run --extra dev pytest
uv run --extra dev python -m build
Run a no-secret source scan before publishing:
git grep -n -I -E 'TOKEN_R=|TOKEN_I=|AuthUserTokenV3_[ri]=[^\"[:space:]]+|gho_|sk-[A-Za-z0-9]|BEGIN (RSA|OPENSSH|PRIVATE) KEY'
Limitations
- Midjourney web APIs are not public APIs and may change without notice.
- The server uses your own Midjourney account and may consume GPU time.
- The returned URLs point to Midjourney CDN assets.
- This does not upload reference images; it is text-prompt only.
License
GPL-3.0-or-later. See LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。