Jimeng
一个为即梦AI打造的MCP服务器，让Claude、Cherry Studio等AI应用直接调用即梦的AI生成能力。基于jimeng-free-api-all开源项目，提供OpenAI兼容接口。 核心功能：文本生成图像（即梦4.0/3.1）、图像合成（多图融合）、文本生成视频（480p-1080p）、图像生成视频（静态转动态）。 支持三种模式：stdio（Claude Desktop）、SSE（Web）、HTTP REST API（跨平台）。Docker一键部署，开箱即用。异步轮询优化，确保长时间
What is Jimeng?
Jimeng is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 一个为即梦ai打造的mcp服务器，让claude、cherry studio等ai应用直接调用即梦的ai生成能力。基于jimeng-free-api-all开源项目，提供openai兼容接口。 核心功能：文本生成图像（即梦4.0/3.1）、图像合成（多图融合）、文本生成视频（480p-1080p）、图像生成视频（静态转动态）。 支持三种模式：stdio（claude desktop）、sse（we...
一个为即梦AI打造的MCP服务器，让Claude、Cherry Studio等AI应用直接调用即梦的AI生成能力。基于jimeng-free-api-all开源项目，提供OpenAI兼容接口。 核心功能：文本生成图像（即梦4.0/3.1）、图像合成（多图融合）、文本生成视频（480p-1080p）、图像生成视频（静态转动态）。 支持三种模式：stdio（Claude Desktop）、SSE（Web）、HTTP REST API（跨平台）。Docker一键部署，开箱即用。异步轮询优化，确保长时间
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 一个为即梦AI打造的MCP服务器，让Claude、Cherry Studio等AI应用直接调用即梦的AI生成能力。基于j
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx jimengConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Jimeng
Jimeng MCP Server connects AI assistants such as Claude and Cherry Studio directly to Jimeng AI's generative media capabilities, letting users produce images and videos through natural language without leaving their AI client. Built on the jimeng-free-api-all open-source backend, it exposes four core tools — text-to-image, image composition, text-to-video, and image-to-video — and supports three transport modes: stdio for Claude Desktop, SSE for web applications, and HTTP REST API for cross-platform integrations. A Docker-based deployment makes the backend straightforward to self-host, and asynchronous polling handles the longer generation tasks reliably.
Prerequisites
- Docker installed for running the jimeng-free-api-all backend service
- Python 3.10 or newer and pip for the MCP server itself
- A Jimeng AI account — session cookie (sessionid) extracted from the browser after login
- An MCP-compatible client such as Claude Desktop
Start the jimeng-free-api-all backend
The MCP server proxies requests through a local API service. Start it with Docker on port 8001.
docker run -it -d --init --name jimeng-free-api-all -p 8001:8000 wwwzhouhui569/jimeng-free-api-all:latestClone and install the MCP server
Clone the repository and install it in editable mode. Add the [all] extra to include SSE and HTTP dependencies if needed.
git clone https://github.com/wwwzhouhui/jimeng-mcp-server
cd jimeng-mcp-server
pip install -e .Obtain your Jimeng session ID
Visit the Jimeng site, log in, open your browser DevTools (F12), navigate to Application > Cookies, and copy the value of the 'sessionid' cookie. This is your JIMENG_API_KEY.
Create your environment file
Copy the example env file and fill in your session ID and the local backend URL.
cp .env.example .env
# Edit .env:
# JIMENG_API_KEY=<your_sessionid>
# JIMENG_API_URL=http://localhost:8001
# JIMENG_MODEL=jimeng-4.5Add the server to Claude Desktop configuration
Open claude_desktop_config.json and add the jimeng entry with your session ID as an environment variable.
{
"mcpServers": {
"jimeng": {
"command": "python",
"args": ["-m", "jimeng_mcp.server"],
"env": {
"JIMENG_API_KEY": "your_sessionid_here",
"JIMENG_API_URL": "http://localhost:8001",
"JIMENG_MODEL": "jimeng-4.5"
}
}
}
}Restart Claude Desktop and test
Fully quit and relaunch Claude Desktop, then ask it to generate an image to confirm the connection works.
Jimeng Examples
Client configuration
claude_desktop_config.json entry for stdio mode. Replace your_sessionid_here with the value copied from your browser cookies.
{
"mcpServers": {
"jimeng": {
"command": "python",
"args": ["-m", "jimeng_mcp.server"],
"env": {
"JIMENG_API_KEY": "your_sessionid_here",
"JIMENG_API_URL": "http://localhost:8001",
"JIMENG_MODEL": "jimeng-4.5"
}
}
}
}Prompts to try
These prompts exercise the four main generation tools exposed by the Jimeng MCP server.
- "Generate a 16:9 image of a futuristic city skyline at dusk in 2K resolution."
- "Create a 10-second 1080p video of waves crashing on a beach."
- "Combine these two product photos into a single composite image."
- "Animate this static product photo into a short looping video."Troubleshooting Jimeng
Authentication error or 401 response from the API
Your sessionid cookie may have expired. Log in to the Jimeng site again, re-copy the sessionid value from DevTools, and update JIMENG_API_KEY in your config or .env file.
Connection refused when the MCP server tries to reach the backend
Confirm the Docker container is running with 'docker ps'. The backend must be up before the MCP server starts. Check that port 8001 is not blocked by a firewall and that JIMENG_API_URL matches the container's published port.
Image or video generation times out
Jimeng AI generation tasks can take 30–90 seconds. The server uses async polling, but if your MCP client has a short timeout, the request may fail. For long tasks, use HTTP REST mode (pip install -e .[http]) which keeps the connection open longer.
Frequently Asked Questions about Jimeng
What is Jimeng?
Jimeng is a Model Context Protocol (MCP) server that 一个为即梦ai打造的mcp服务器，让claude、cherry studio等ai应用直接调用即梦的ai生成能力。基于jimeng-free-api-all开源项目，提供openai兼容接口。 核心功能：文本生成图像（即梦4.0/3.1）、图像合成（多图融合）、文本生成视频（480p-1080p）、图像生成视频（静态转动态）。 支持三种模式：stdio（claude desktop）、sse（web）、http rest api（跨平台）。docker一键部署，开箱即用。异步轮询优化，确保长时间 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Jimeng?
Follow the installation instructions on the Jimeng GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Jimeng?
Jimeng works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Jimeng free to use?
Yes, Jimeng is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Jimeng Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Jimeng? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Jimeng in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Jimeng?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.