impeccable
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
Generate images and videos with Seedance, Veo, Wan, Grok, GPT-Image and Nano Banana via one MCP.
Skills that teach the AI this kind of work; they work alongside this one
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.
Create beautiful slides on the web using a coding agent's frontend skills
Lists are ordered by a usage score (out of 100) built from these parts
| Popularity | 0/80 | GitHub stars or weekly downloads: the larger counts 60, the smaller 20 |
|---|---|---|
| Freshness | 12/12 | Full marks for a release or code change within 30 days |
| Still answering | 8/8 | The cloud endpoint answered at the last check |
| Usage score | 20/100 |
Quality: Passed 3/5 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)
Pick the AI app you use, then copy the settings.
Let your AI install it with one sentence
Please install Jiguang AI Media (极光 AI 图片 / 视频生成). Follow https://mcp.popnx.com/i/tk-jiguang-ai-media.md, show me the commands and wait for my OK before running them.Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads
Passed 3/5 checks · What you ask goes through the maker’s server (vi.91jiguang.com) · ✓ Commands checked Nov 13, 2026
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude · about 5 min
You need a Jiguang AI Media (极光 AI 图片 / 视频生成) key (create it on the maker’s site) · Set it up once on claude.ai or the desktop app, then use it in chat · free accounts can add 1 · on Team/Enterprise an Owner adds it
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
CustomizeConnectors
Copy each value into the field with the same name in Claude, then click Continue
Jiguang AI Media (极光 AI 图片 / 视频生成)https://vi.91jiguang.com/api/mcpUnder Request headers, add this name and value
AuthorizationBearer <paste your key here>Paste the key only into the app’s field, never into a chat or to anyone
Click Continue past the sign-in settings Claude detected · under Authentication choose what the maker says (Sign in now, Sign in when needed or No sign in), then click Add
+ConnectorsJiguang AI Media (极光 AI 图片 / 视频生成)
Use Jiguang AI Media (极光 AI 图片 / 视频生成) and tell me what you can do for me, then show me one thing✓ If Claude says it is using Jiguang AI Media (极光 AI 图片 / 视频生成) or shows a Jiguang AI Media (极光 AI 图片 / 视频生成) tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
ChatGPT cannot connect Jiguang AI Media (极光 AI 图片 / 视频生成) yet
Jiguang AI Media (极光 AI 图片 / 视频生成) needs your own key to connect, but OpenAI’s help page only describes OAuth sign-in; there is no key option we could verify
A · Use an app that can connect Jiguang AI Media (极光 AI 图片 / 视频生成)
B · Others in Design, images & audio that work with ChatGPT
Picked from the most used in the same category, only ones that connect by address with no key
Works with Claude Code · about 5 min
You need a Jiguang AI Media (极光 AI 图片 / 视频生成) key (create it on the maker’s site)
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
Mac: press Command+Space and type Terminal · Windows: open PowerShell
claude mcp add --transport http --scope user ai-media https://vi.91jiguang.com/api/mcp --header 'Authorization: Bearer your-value'Replace “your-value” with your key before pressing Enter
Paste the key only into the app’s field, never into a chat or to anyone
You should see Jiguang AI Media (极光 AI 图片 / 视频生成) listed as connected
Use Jiguang AI Media (极光 AI 图片 / 视频生成) and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using Jiguang AI Media (极光 AI 图片 / 视频生成) or shows a Jiguang AI Media (极光 AI 图片 / 视频生成) tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Cursor · about 5 min
You need a Jiguang AI Media (极光 AI 图片 / 视频生成) key (create it on the maker’s site)
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
In the Jiguang AI Media (极光 AI 图片 / 视频生成) settings, Authorization is empty; add your key and save
Paste the key only into the app’s field, never into a chat or to anyone
Use Jiguang AI Media (极光 AI 图片 / 视频生成) and tell me what you can do for me, then show me one thing✓ If Cursor says it is using Jiguang AI Media (极光 AI 图片 / 视频生成) or shows a Jiguang AI Media (极光 AI 图片 / 视频生成) tool in the answer, you are connected
Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with VS Code · about 5 min
You need a Jiguang AI Media (极光 AI 图片 / 视频生成) key (create it on the maker’s site)
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
In the Jiguang AI Media (极光 AI 图片 / 视频生成) settings, Authorization is empty; add your key and save
Paste the key only into the app’s field, never into a chat or to anyone
Use Jiguang AI Media (极光 AI 图片 / 视频生成) and tell me what you can do for me, then show me one thing✓ If VS Code says it is using Jiguang AI Media (极光 AI 图片 / 视频生成) or shows a Jiguang AI Media (极光 AI 图片 / 视频生成) tool in the answer, you are connected
Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.
Address for apps that connect over the web
https://vi.91jiguang.com/api/mcpJSON settings are under “For developers” below
Claude Code
claude mcp add --transport http --scope user ai-media https://vi.91jiguang.com/api/mcp --header 'Authorization: Bearer your-value'Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"ai-media": {
"url": "https://vi.91jiguang.com/api/mcp",
"headers": {
"Authorization": "Bearer your-value"
}
}
}
}VS Code (mcp.json)
{
"servers": {
"ai-media": {
"type": "http",
"url": "https://vi.91jiguang.com/api/mcp",
"headers": {
"Authorization": "Bearer your-value"
}
}
}
}Descriptions are as written by the maker.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Connect over the internet in
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
The server asks you to sign in before it lists its tools.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 20, 2026
The registry name was verified with the GitHub account tk-jiguang, which owns the repo
Code last changed 7 days ago
Uses MIT
Refused access (HTTP 401) without offering OAuth sign-in. It may need a key, or it may be blocking bots; not confirmed.
Needs a key or token that you copy and paste yourself
Not checked yet; we read the tool list when we check the endpoint
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/servers/tk-jiguang-ai-media)Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
No reviews yet
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 5 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: Authorization
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed 7 days ago, and the latest version (1.0.0) reached the registry 7 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT on the web (full MCP on Business and above; Pro read-only).
In the same category: HyperFrames by HeyGen, Pascal 3D Editor, draw.io, Figma MCP Server, Remocn: Remotion MCP server
Same category, other makers, commands already checked. Official ones first, then by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Official HyperFrames by HeyGen: the best AI video editor in chat. Captions, motion graphics, MP4.
Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.
Create draw.io diagrams in chat from Mermaid or XML, shown live and interactive. 10,000+ shapes.
Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.
Hosted MCP for Remotion videos: search Remocn components, read docs, plan a video, preview it.
| This one Jiguang AI Media (极光 AI 图片 / 视频生成) | HyperFrames by HeyGen | Pascal 3D Editor | draw.io | Figma MCP Server | Remocn: Remotion MCP server | |
|---|---|---|---|---|---|---|
| Runs where | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Cloud or install on your computer | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install |
| Needs a key | Yes | No | No | No | No | No |
| Add with + in Claude | No | Yes | No | No | Yes | No |
| Basic checks | 3/5 | 4/4 | 5/5 | 4/4 | 4/4 | 4/4 |
| License | MIT | Apache-2.0 | MIT | Apache-2.0 | – | MIT |
| Price | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry |
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
让 Claude Code、Cursor、Codex、Trae 等 AI Agent 直接调用图片和视频生成模型(Seedance、Veo、Wan、Grok、GPT-Image、Nano Banana 等)的远程 MCP 服务,同一套能力也提供 REST API。由 极光 AI(TK极光旗下的 AI 创作工作台)提供。
English: A hosted (remote) MCP server and REST API that lets AI agents generate images and videos with models such as Seedance, Veo, Wan, Grok, GPT-Image and Nano Banana. Pay-as-you-go credits, no local install. See README.en.md.
https://vi.91jiguang.com/api/mcp(Streamable HTTP)https://vi.91jiguang.com/api/v1Authorization: Bearer ,API Key 在开发者中心创建这个仓库放的是接入配置、示例代码和一个 Agent Skill。服务本身托管在极光 AI,不需要自己部署。
| 场景 | 说明 |
|---|---|
| 电商商品图 | 商品主图、模特上身图、场景图、海报,支持参考图 |
| 带货短视频 | 文生视频、图生视频,部分模型支持参考视频 |
| 放进画布继续改 | 生成结果可以放进极光 AI 创作画布,在网页里接着编辑 |
模型、参数和价格会调整,一律以接口实时返回为准(MCP 的 list_image_models / list_video_models,或 REST 的 GET /models)。
下面是 2026-11-13 03:58(北京时间)的工作台价格快照(人民币按「体验档」档位(¥30 = 60 积分)折算,¥0.5/积分)。模型会上新、下线和调价,以[实时价格表](https://vi.91jiguang.com/model-pricing)为准;通过接口调用时,开放了哪些模型、每个模型当前的价格,都以接口 GET /models 的返回为准。
「/次」是每次生成扣的积分;「/张」「/条」是按数量计费,一次生成多张图或多条视频时乘以数量。
图片模型
| 模型 | 价格 | 约合人民币 | 分辨率 |
|---|---|---|---|
| GPT-Image-2.6 GIF动图 | 0.06 积分/次 | ¥0.03 | 1K |
| GPT-Image-2.6 最强 | 0.06–0.12 积分/次 | ¥0.03–¥0.06 | 1K / 2K / 4K |
| GPT-Image-2.5-sunburst | 0.06–0.12 积分/次 | ¥0.03–¥0.06 | 1K / 2K / 4K |
| GPT-Image-2.5-flare 快速 | 0.06–0.12 积分/次 | ¥0.03–¥0.06 | 1K / 2K / 4K |
| GPT-Image-2 | 0.06–0.12 积分/张 | ¥0.03–¥0.06 | 1K / 2K / 4K |
| Nano Banana 2.1 | 0.15 积分/张 | ¥0.075 | 1K |
| Gemini 3.1 Flash Image | 0.15–0.18 积分/张 | ¥0.075–¥0.09 | 1K / 2K |
视频模型
| 模型 | 价格 | 约合人民币 | 时长 | 分辨率 |
|---|---|---|---|---|
| Grok1.5 Pro | 0.6–5.2 积分/次 | ¥0.3–¥2.6 | 3–15 秒 | 480p / 720p |
| MiniMax H3 | 1.3–3 积分/次 | ¥0.65–¥1.5 | 5–15 秒 | 480p / 768p |
| Gemini Omni 1.2 | 1.4–2.5 积分/条 | ¥0.7–¥1.25 | 4–15 秒 | 720p |
| Gemini Omni | 1.4–3.6 积分/条 | ¥0.7–¥1.8 | 4–20 秒 | 720p |
| Veo 3.1 Lite | 1.8 积分/条 | ¥0.9 | 8 秒 | 720p |
| Veo 3.1 Fast | 2–2.4 积分/条 | ¥1–¥1.2 | 8 秒 | 720p / 1080p |
| Muse | 2–4 积分/次 | ¥1–¥2 | 5–10 秒 | 720p |
| Veo 3.1 满血 | 2.5–3 积分/条 | ¥1.25–¥1.5 | 8 秒 | 720p / 1080p |
| Seedance2.0-Mini | 4–11 积分/次 | ¥2–¥5.5 | 5–15 秒 | — |
| Seedance2.0 Fast | 5 积分/次 | ¥2.5 | 4–15 秒 | 720p |
| Seedance2.5 | 8–35 积分/次 | ¥4–¥17.5 | 5–30 秒 | 720p / 480p |
| Wan 3.0 | 12–28 积分/次 | ¥6–¥14 | 5–30 秒 | 480p / 720p |
| Seedance2.0 满血 | 14 积分/次 | ¥7 | 4–15 秒 | 720p |
| Seedance2.5 按次 | 20–30 积分/次 | ¥10–¥15 | 5–30 秒 | 720p |
先在开发者中心创建 API Key,放进环境变量 AI_MEDIA_API_KEY(不要写进代码仓库、截图或日志)。开发者中心也可以选好 Agent 后一键复制带 Key 的接入指令。
Claude Code
claude mcp add --transport http ai-media https://vi.91jiguang.com/api/mcp --header "Authorization: Bearer $AI_MEDIA_API_KEY"
Cursor(.cursor/mcp.json 或全局 ~/.cursor/mcp.json)
{
"mcpServers": { "ai-media": { "url": "https://vi.91jiguang.com/api/mcp", "headers": { "Authorization": "Bearer " } } } }
其他支持 MCP 的客户端(通用写法)
{
"mcpServers": { "ai-media": { "type": "http", "url": "https://vi.91jiguang.com/api/mcp", "headers": { "Authorization": "Bearer " } } } }
不同客户端的字段名略有差异:type 可能写作 http、streamableHttp 或 streamable-http,地址字段可能叫 url 或 httpUrl,按各自的配置格式来。
| 工具 | 用途 | 是否扣积分 |
|---|---|---|
list_image_models / list_video_models | 查可用模型、参数组合和价格 | 否 |
create_image_generation / create_video_generation | 创建生成任务(需传 confirmed: true 和稳定的 idempotency_key) | 是,失败退回 |
get_generation | 查进度和结果 | 否 |
prepare_image_upload | 参考图是本地文件时申请上传地址;网络图片链接直接用,不必上传 | 否 |
list_canvases / create_canvas / get_canvas | 画布列表、新建、读取 | 否 |
import_generation_to_canvas | 把成功的图片或视频放进画布 | 否 |
三步:查模型 → 创建任务 → 轮询结果。完整示例见 examples/。
# 1. 查模型(不扣积分)
curl "https://vi.91jiguang.com/api/v1/models" -H "Authorization: Bearer $AI_MEDIA_API_KEY"
curl -X POST "https://vi.91jiguang.com/api/v1/generations" \ -H "Authorization: Bearer $AI_MEDIA_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: demo-001" \ -d '{ "model": "<第 1 步返回的模型 id>", "input": { "prompt": "白色纯棉圆领 T 恤商品主图,纯白背景,1:1 构图" }, "parameters": {} }'
curl "https://vi.91jiguang.com/api/v1/generations/<任务 id>" -H "Authorization: Bearer $AI_MEDIA_API_KEY"
examples/quickstart.py:只用 Python 标准库,按最低价挑一个图片模型出一张图examples/quickstart.mjs:Node.js 18+ 版本skills/ai-media/SKILL.md 是一份可以放进 Claude Code 等支持 Skill 的 Agent 里的技能说明:什么时候用、先查模型再生成、扣费前确认、结果怎么交给用户。
需要自己部署吗? 不需要。MCP 服务和接口都托管在极光 AI,这个仓库只有配置和示例。
多少钱? 按积分计费,每个模型每次生成的积分和人民币参考价见模型价格表,数据实时生成。
生成失败会扣积分吗? 不会,失败自动退回。
参考图要先上传吗? 网络图片链接(任何公开可访问的 http(s) 地址)直接放进 input.images;只有本地文件才需要先申请上传地址。
和 TK极光插件是什么关系? 同一家的两个产品。TK极光插件是 TikTok Shop 商家后台里用的浏览器插件(商品机会提报、秒杀活动批量创建、选品采集等),官网 https://www.91jiguang.com;极光 AI 是 AI 创作工作台和这套开发者接口。