jimeng_visual_generation
This server provides AI-powered visual generation via Volcengine APIs, enabling image and video creation from text, references, or multi-modal inputs.
Generate images from text prompts (T2I) or reference images (I2I), with adjustable size, seed, and output format.
Generate videos from text (T2V), images (I2V), or mixed multi-modal inputs (images, videos, audio) with control over ratio, resolution, duration, watermark, audio track, and last-frame return.
Query video generation task status by Task ID, retrieving the output URL once complete.
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., "@jimeng_visual_generation Generate an image of a futuristic city at night"
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.
Jimeng 视觉生成 MCP 服务器
基于 Volcengine(火山引擎)Jimeng 视觉生成 API 的 MCP 服务器。通过模型上下文协议(MCP)提供图像和视频生成功能。
功能
文本生成图像(T2I):根据文本提示生成图像
图像到图像(I2I):基于提示和参考图像对图像进行变换
多图融合:合成多张参考图像
文本生成视频(T2V):根据文本提示生成视频
图像到视频(I2V):从首帧或首帧+末帧图像生成视频
自动本地文件支持:可传入图像公网URL,同时支持本地文件路径,程序会自动将其转换为 Base64
Related MCP server: jimeng4-mcp
安装
选项 1:通过 pip 安装
pip install jimeng_visual_generation选项 2:直接使用 uvx 运行(推荐)
无需安装。uvx 会自动下载并运行该包:
uvx jimeng_visual_generation在 VS Code / Cursor / Claude Desktop 中的配置
将下列内容添加到你的 MCP 配置文件:
VS Code:
~/.vscode/mcp.json或 工作区设置Cursor:Settings -> MCP Servers
Claude Desktop:
%APPDATA%\Claude\claude_desktop_config.json
示例配置(使用环境变量)
{
"mcpServers": {
"jimeng_visual_generation": {
"command": "uvx",
"args": ["jimeng_visual_generation"],
"env": {
"VOLC_API_KEY": "your_volcengine_api_key_here",
"VOLC_IMAGE_MODEL": "doubao-seedream-5-0-pro-260628",
"VOLC_VIDEO_MODEL": "doubao-seedance-2-5-260628"
}
}
}
}环境变量
变量 | 是否必需 | 描述 |
| ✅ 必需 | 你的 Volcengine API Key |
| 可选 | 图像模型 ID(默认: |
| 可选 | 视频模型 ID(默认: |
可用工具
generate_image
使用文本提示和可选参考图像生成图像。支持最新的 Doubao-Seedream-5.0-pro 精准图层编辑。
参数:
prompt(必需):描述目标图像的文本image_urls(可选):参考图像列表(支持 URL、Base64 或本地文件路径)model(可选):使用的模型 ID 或 Endpoint ID(例如doubao-seedream-5-0-pro-260628)size(可选):图像尺寸比例(支持 "1:1", "16:9", "2K", "4K" 等,禁止使用ratio)
generate_video
创建视频生成任务。支持多种生成模式(包括最新的 Seedance 2.5 30秒超长叙事与全模态参考):
文本生成视频 (T2V):不提供图像、视频、音频输入,只提供
prompt。首帧/尾帧生视频 (I2V):提供 1-2 张图像。
多模态参考生视频 (Seedance 2.5 / 2.0 / 2.0-mini):可混合提供图像(最多9张)、参考视频(最多3个)和参考音频(最多3个),支持本地文件自动转换。
30秒超长叙事 (Seedance 2.5):最高支持 30 秒长视频生成。
参数:
prompt(可选):视频描述的文本提示词image_urls(可选):输入参考图像列表(支持 URL、Base64 或本地文件路径,最多 9 张)video_urls(可选):参考视频列表(支持 URL 或本地文件路径,最多 3 个,Seedance 2.5 支持 ≤ 30s,2.0 支持 ≤ 15s)audio_urls(可选):参考音频列表(支持 URL 或本地文件路径,最多 3 个)image_roles(可选):为image_urls显式指定的角色列表(例如["reference_image", "first_frame"])model(可选):使用的模型 ID 或 Endpoint ID(如doubao-seedance-2-5-260628、doubao-seedance-2-0-mini-260615等)ratio(可选):宽高比(例如:"16:9"、"9:16",禁止在图片生成里使用该参数)resolution(可选):分辨率("720p" 或 "1080p",mini 与 fast 模型支持至 720p,2.5 与标准 2.0 支持 1080p)duration(可选):视频时长(秒,Seedance 2.5 支持 4-30s,Seedance 2.0/2.0-mini 支持 4-15s,默认 5)return_last_frame(可选):是否返回生成的视频最后一帧图像 URL,适用于连续生成
get_video_task_result
查询视频生成任务的状态和结果。
参数:
task_id(必需):由generate_video返回的任务 ID
📄 开源协议 (License)
本项目基于 MIT License 开源。
💖 赞助 (Sponsorship)
维护开源项目不易,如果您觉得 jimeng_visual_generation 对您有帮助,欢迎请作者喝杯咖啡!
平台 | 链接 | 支付方式 |
爱发电 (Afdian) | 微信, 支付宝 |
Available Tools
3 toolsgenerate_imageA
Generate images using Volcengine visual generation API.
CRITICAL INSTRUCTIONS FOR AI AGENTS:
For image size, ONLY use the 'size' parameter (e.g., size="16:9"). DO NOT pass a 'ratio' or 'width'/'height' parameter.
If the user provides a custom Endpoint ID (starts with 'ep-'), you MUST pass it into the 'model' parameter.
Capabilities:
Text-to-Image: Provide 'prompt' and 'size'.
Image-to-Image: Provide 'prompt' AND 'image_urls' (list containing 1 image string).
Inputs: params (required). Returns: result
generate_videoA
Create a video generation task using Volcengine API.
CRITICAL INSTRUCTIONS FOR AI AGENTS:
This tool ONLY submits the task. It returns a Task ID. You MUST subsequently call
get_video_task_resultin a loop (wait 5-10s between calls) to retrieve the actual video URL.Use 'ratio' for video proportions (e.g., ratio="16:9"). DO NOT use 'size' or 'width'/'height'.
If user provides an Endpoint ID ('ep-...'), pass it to the 'model' parameter.
Capabilities:
Text-to-Video: Provide 'prompt' and 'ratio'.
Image-to-Video: Provide 'image_urls' array + optional 'prompt'.
Multi-Modal (Seedance 2.0): Mix 'image_urls' (up to 9), 'video_urls' (up to 3), and 'audio_urls' (up to 3).
Inputs: params (required). Returns: result
get_video_task_resultA
Query the status of a video generation task using the Task ID returned by generate_video.
CRITICAL INSTRUCTIONS FOR AI AGENTS:
Video generation takes time (often 1-3 minutes).
If the returned status is "ordered" or "running", DO NOT tell the user it failed. Ask the user to wait, and call this tool again after 10-15 seconds.
Once the status is "succeeded", the response will contain the download URL.
Inputs: params (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool targets a distinct action: image generation, video submission, and video result polling. No overlap in functionality.
All tools follow a consistent verb_noun pattern in snake_case: generate_image, generate_video, get_video_task_result.
Three tools is minimal but covers the core workflows of image generation and video generation with polling. Slightly thin but reasonable for a focused server.
Missing operations like listing or deleting generated content, and no image editing or video task cancellation. Gaps exist but essential flows are present.
Maintenance
Related MCP Connectors
MCP server for Qwen Image 3 AI image generation
MCP server for ByteDance Seedream AI image generation
MCP server for Hailuo (MiniMax) AI video generation
MCP server for Wan AI video generation
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that generates high-quality images through Volcano Engine's Doubao model, supporting bilingual prompts, multiple resolutions, and parameter controls like seed and guidance scale.34 PyPI2MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server providing multi-modal generation tools based on Volcengine's Jimeng AI, supporting high-quality 4K image creation, intelligent image editing, and video generation. It enables users to perform complex visual tasks directly within clients like Cursor and Claude Desktop.13 npmMIT
- AlicenseAqualityDmaintenanceMCP server integrating VolcEngine's image generation capabilities, enabling text-to-image, image-to-image, and image set generation for AI applications.426 npmMIT
- AlicenseAqualityDmaintenanceMCP server for generating images using Volcano Engine's Jimeng AI, supporting the latest Seedream4.0 model.119 npm3MIT