Agnes Media MCP Server
This server enables AI-powered image and video generation directly from Claude Desktop using natural language, with results automatically saved locally.
Image Generation (
agnes_generate_image): Generate images from text prompts (text-to-image) or transform existing images (image-to-image) using Agnes Image 2.1 Flash. Configurable options include output size (1K–4K), aspect ratios (1:1, 16:9, 9:16, etc.), seed, negative prompt, and optional inline previews.Video Generation (
agnes_generate_video): Create videos using Agnes Video V2.0 via text-to-video, image-to-video (single image URL), or keyframe transition (multiple image URLs). Configurable parameters include resolution, frame count (up to 441, 8n+1), frame rate (1–60 fps), seed, and negative prompt.Async Video Polling (
agnes_get_video_status): Since video generation takes minutes, the server returns avideo_idimmediately. Poll this tool to check task progress and optionally download the final.mp4when complete.Local File Saving: All generated images and videos are automatically saved to configurable local directories (default: system Pictures/Videos folders under
AgnesOutputs/).Network Resilience: API calls include automatic retry logic (up to 4 attempts) to handle transient errors or rate limits.
Cross-Platform: Runs on Node.js, compatible with macOS and Windows, and integrates seamlessly with Claude Desktop.
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., "@Agnes Media MCP Server generate a 16:9 cyberpunk city wallpaper"
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.
Agnes Media MCP Server
一个用于 Claude Desktop 的本地 MCP 服务器,内置:
Agnes Image 2.1 Flash (
agnes-image-2.1-flash) — 文生图 / 图生图Agnes Video V2.0 (
agnes-video-v2.0) — 文生视频 / 图生视频 / 关键帧动画(异步)
接入后,在 Claude Desktop 里用自然语言即可生成图片和视频,结果自动落盘到本地目录。
跨平台:服务器由 Node 运行,macOS 与 Windows 均可使用。
工具
工具 | 说明 |
| 生成图片。默认文生图;传 |
| 创建视频任务并短等待(默认 45s)。若在等待窗口内完成则直接下载 mp4;否则立即返回 |
| 按 |
视频时长:seconds = num_frames / frame_rate。num_frames 必须 ≤ 441 且满足 8n+1(如 81≈3s、121≈5s、241≈10s、441≈18s @ 24fps)。
为什么视频要两步:视频生成通常需要数分钟,超过单次 MCP 请求的超时(约 60s)。因此 agnes_generate_video 只在客户端超时预算内(wait_seconds,默认 45s、上限 50s)内联等待——快的视频一次返回;慢的立即交回 video_id,用 agnes_get_video_status(download:true)每隔约 15s 轮询直到 completed 即可拿到文件。
Related MCP server: Jimeng MCP Server
安装与构建
npm install
npm run build生成 dist/index.js。
配置(环境变量)
变量 | 必填 | 默认 | 说明 |
| 是 | — | Agnes AI API Key |
| 否 | 系统图片/视频文件夹 | 覆盖输出根目录(设置后图片→ |
| 否 |
| API 网关地址 |
默认落盘位置:不设 AGNES_OUTPUT_DIR 时,图片保存到系统"图片"文件夹、视频保存到系统"视频"文件夹,各自放在 AgnesOutputs/ 子目录下。Windows 上会读取真实的已知文件夹路径(支持重定向,如 H:\用户文件\图片);macOS/Linux 回退到 ~/Pictures、~/Videos。
网络重试:所有 API 调用与文件下载都带自动重试(网络失败或 429/5xx 时等 2 秒重试,共 4 次尝试),以应对偶发的网络抖动。
接入 Claude Desktop
编辑 Claude Desktop 配置文件:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json(不同版本的路径可能不一样)
加入(把路径换成本机 dist/index.js 的绝对路径):
{
"mcpServers": {
"agnes-media": {
"command": "node",
"args": ["/绝对路径/图片和视频MCP/dist/index.js"],
"env": {
"AGNES_API_KEY": "你的Key",
"AGNES_OUTPUT_DIR": "可选自定义输出目录"
}
}
}
}Windows 下
args路径示例:"C:\\Users\\you\\projects\\图片和视频MCP\\dist\\index.js"(反斜杠需转义,或用正斜杠)。
保存后完全重启 Claude Desktop。连接成功后即可对 Claude 说:“生成一张 16:9 的霓虹灯城市壁纸”。
本地调试
用官方 MCP Inspector 手动调用工具:
AGNES_API_KEY=你的Key npm run inspect在 Inspector 里:
agnes_generate_image—prompt任意,size: "2K",ratio: "16:9"→ 检查系统「图片」文件夹下AgnesOutputs/出图。agnes_generate_video—num_frames: 121, frame_rate: 24→ 等待轮询完成,检查系统「视频」文件夹下AgnesOutputs/出 mp4。agnes_get_video_status— 传上一步的video_id。
注意事项
日志走 stderr,stdout 专供 MCP 协议,请勿改动。
视频为异步生成,可能需要数分钟;服务器会阻塞轮询(默认间隔 5s、超时 10 分钟)。超时后可用
agnes_get_video_status继续查询。图生图不需要
tags;response_format由服务器自动放进extra_body。定价当前为 $0(图片 / 视频),可放心联调。
Available Tools
3 toolsagnes_generate_imageA
Generate an image with Agnes Image 2.1 Flash. Text-to-image by default; pass image_urls to do image-to-image (transform/restyle while preserving composition). The result is saved to the local output directory and a preview is returned inline.
Inputs: prompt (required), size, ratio, image_urls, +1 more.
agnes_generate_videoA
Start an Agnes Video V2.0 generation (async). Text-to-video by default; pass image_url for image-to-video, or keyframe_urls (2+) for keyframe transitions. Video generation takes minutes, longer than an MCP request can block. This tool creates the task and waits up to wait_seconds for it to finish: if it completes in time, the mp4 is downloaded locally and its path returned; otherwise it returns the video_id immediately — poll agnes_get_video_status with that id (download:true) to fetch the result when ready. Duration = num_frames / frame_rate. num_frames must be <=441 and of the form 8n+1.
Inputs: prompt (required), seed, width, height, +6 more.
agnes_get_video_statusA
Check the status of an Agnes video task by video_id. Returns status/progress, and if completed, the remote URL. Optionally downloads the mp4 locally when ready.
Inputs: video_id (required), download.
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 operation: image generation, video generation (async), and video status retrieval. No overlap in purpose.
All tools follow a consistent 'agnes_verb_noun' pattern with underscores (e.g., generate_image, get_video_status). No mixing of styles.
3 tools is minimal but appropriate for the focused scope of image and video generation. Could be expanded with list/delete utilities, but not underpowered.
Covers core generation and status polling, but lacks list/delete or cancel operations for videos, and no tool for managing images beyond generation.
Related MCP Connectors
AI video generation MCP server for Kling, MiniMax, Luma & Hunyuan with prompt blueprints.
MCP server for Qwen Image 3 AI image generation
MCP server for Grok Imagine AI video generation
MCP server for Wan AI video generation
Related MCP Servers
- AlicenseAqualityCmaintenanceMCP server for AI-powered image, audio, and video generation, enabling media creation directly from Claude, Cursor, and other MCP clients.1144 npmMIT
- FlicenseNot gradedqualityBmaintenanceA Model Context Protocol server for AI image and video generation using Jimeng AI, enabling text-to-image, image composition, text-to-video, and image-to-video through Claude Desktop and other MCP clients.84-
- FlicenseNot gradedqualityDmaintenanceA local MCP server that gives Claude Desktop full video editing capabilities via FFmpeg, Whisper, and yt-dlp.-
- AlicenseNot gradedqualityDmaintenanceA powerful MCP server that brings AI vision capabilities to Claude Desktop. Analyze images and videos using OpenAI GPT-4o, Claude, or any compatible vision API.31 npmMIT