Visual Loop MCP Server
Enables AI clients to write, run, and visually render code in a single loop, combining secure execution via Judge0/Codebox with Playwright screenshots.
README
<div align="center">
<!-- Animated Header Banner --> <img src="https://capsule-render.vercel.app/api?type=waving&color=0:6C63FF,50:A855F7,100:EC4899&height=220§ion=header&text=Visual%20Loop%20MCP&fontSize=50&fontColor=FFFFFF&fontAlignY=35&desc=Execute%20%E2%80%A2%20Render%20%E2%80%A2%20Verify&descSize=20&descAlignY=55&animation=fadeIn" width="100%" alt="Visual Loop MCP Header"/>
<br/>
<br/>
<p align="center"> <strong>A production-ready MCP server that combines <em>secure code execution</em> with <em>visual rendering</em> β giving multimodal AI clients the power to write, run, and <em>see</em> code in one seamless loop.</strong> </p>
<br/>
π Quick Start β’ π Documentation β’ π§ Configuration β’ π€ Claude Desktop β’ π‘ API Reference
<br/>
</div>
β¨ Why Visual Loop?
Most AI coding assistants can write code β but they can't see the result. Visual Loop MCP closes that gap by providing a single tool that:
<table> <tr> <td width="60" align="center">β‘</td> <td><strong>Executes code securely</strong> via Judge0/Codebox sandboxed runtime</td> </tr> <tr> <td align="center">πΌοΈ</td> <td><strong>Renders visual output</strong> using Playwright headless Chromium</td> </tr> <tr> <td align="center">πΈ</td> <td><strong>Returns screenshots</strong> alongside console output in a single multimodal response</td> </tr> <tr> <td align="center">π</td> <td><strong>Enables iterative UI development</strong> β AI sees its own output and self-corrects</td> </tr> </table>
[!TIP] Think of it as giving your AI eyes β it can now verify layouts, catch visual bugs, and iterate on designs without human intervention.
ποΈ Architecture
ββββββββββββββββββββββββββββββββ
β AI Client β
β (Claude Desktop / Cursor) β
ββββββββββββββββ¬ββββββββββββββββ
β
stdio (JSON-RPC 2.0)
β
ββββββββββββββββΌββββββββββββββββ
β Visual Loop MCP Server β
β β
β βββββββββββββββββββββββββ β
β β Phase A: Execute β β ββββββββββββββββββββ
β β Code Validation βββββΌβββββΆβ Judge0/Codebox β
β β β β β (Sandboxed API) β
β βββββββββββββββββββββββββ β ββββββββββββββββββββ
β β
β βββββββββββββββββββββββββ β
β β Phase B: Render β β ββββββββββββββββββββ
β β Visual Screenshot βββββΌβββββΆβ Playwright β
β β β β β (Headless Chrome) β
β βββββββββββββββββββββββββ β ββββββββββββββββββββ
β β
β βββββββββββββββββββββββββ β
β β Phase C: Cleanup β β Temp files removed
β β Resource Disposal β β Browser closed
β βββββββββββββββββββββββββ β
β β
βββββββββββββββββββββββββββββββββ
<div align="center">
graph LR
A[π€ AI Client] -->|stdio JSON-RPC| B[π Visual Loop MCP]
B -->|POST /submissions| C[β‘ Judge0 Codebox]
B -->|file:// render| D[π Playwright]
C -->|stdout / stderr| B
D -->|base64 PNG| B
B -->|multimodal response| A
style A fill:#6C63FF,stroke:#4F46E5,color:#fff,stroke-width:2px
style B fill:#A855F7,stroke:#9333EA,color:#fff,stroke-width:2px
style C fill:#F59E0B,stroke:#D97706,color:#fff,stroke-width:2px
style D fill:#10B981,stroke:#059669,color:#fff,stroke-width:2px
</div>
π¦ Prerequisites
| Requirement | Version | Purpose |
|---|---|---|
| <img src="https://img.shields.io/badge/-Node.js-339933?logo=node.js&logoColor=white&style=flat-square" /> | β₯ 20.0 |
Runtime environment |
| <img src="https://img.shields.io/badge/-npm-CB3837?logo=npm&logoColor=white&style=flat-square" /> | β₯ 10.0 |
Package management |
| <img src="https://img.shields.io/badge/-Docker-2496ED?logo=docker&logoColor=white&style=flat-square" /> | Any | Judge0 container hosting |
π Quick Start
1οΈβ£ Start the Judge0 Sandbox
# Pull and run Judge0 CE in Docker
docker run -d -p 2358:2358 --name judge0 judge0/judge0-ce
2οΈβ£ Install & Build
# Clone the repository
git clone https://github.com/IqbalHere/-Visual-Loop-MCP-Server.git
cd -Visual-Loop-MCP-Server
# Install dependencies
npm install
# Install Playwright Chromium (minimal footprint)
npx playwright install chromium
# Build the TypeScript project
npm run build
3οΈβ£ Run the Server
<details> <summary><strong>π§ macOS / Linux</strong></summary>
CODEBOX_URL=http://localhost:2358 CODEBOX_TOKEN=your_token npm start
</details>
<details> <summary><strong>πͺ Windows (PowerShell)</strong></summary>
$env:CODEBOX_URL = "http://localhost:2358"
$env:CODEBOX_TOKEN = "your_token"
npm start
</details>
π§ Configuration
| Variable | Required | Description |
|---|---|---|
CODEBOX_URL |
β | Base URL of your Judge0/Codebox instance |
CODEBOX_TOKEN |
β | Auth token for the Codebox API (omit if no auth) |
[!NOTE] If
CODEBOX_URLis unset, the server gracefully skips code execution and only performs visual rendering. No crash, no fuss.
π€ Claude Desktop Integration
Add this to your Claude Desktop configuration file:
| Platform | Config Path |
|---|---|
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Windows | %APPDATA%\Claude\claude_desktop_config.json |
{
"mcpServers": {
"visual-loop": {
"command": "node",
"args": ["C:/absolute/path/to/visual-loop-mcp/build/index.js"],
"env": {
"CODEBOX_URL": "http://localhost:2358",
"CODEBOX_TOKEN": "your_token_here" // optional
}
}
}
}
[!IMPORTANT] Replace the path in
argswith the absolute path to your cloned project. Use forward slashes (/) even on Windows.
After saving, restart Claude Desktop. The execute_and_render tool will appear in the tool picker. π
π‘ Tool Reference
execute_and_render
The single, powerful tool exposed by this server.
AI writes code β Codebox validates logic β Playwright renders visuals β AI sees the result
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
source_code |
string |
β | β | Raw HTML/CSS/JS source code to execute and render |
language_id |
number |
β | β | Judge0 language ID (see table below) |
viewport_width |
number |
β | 1280 |
Browser viewport width in pixels |
viewport_height |
number |
β | 720 |
Browser viewport height in pixels |
Response Format
The tool returns a multimodal MCP content array containing both text and image:
{
"content": [
{
"type": "text",
"text": "[Codebox] Status: Accepted (id: 3)\nββ stdout ββ\nHello, world!\n\nExecution time: 0.012s | Memory: 3456 KB"
},
{
"type": "image",
"data": "<base64-encoded-PNG-screenshot>",
"mimeType": "image/png"
}
]
}
ποΈ Supported Languages
| Language | ID | Language | ID |
|---|---|---|---|
| π¨ JavaScript (Node.js) | 63 |
π Python 3 | 71 |
| π· TypeScript | 74 |
β Java | 62 |
| βοΈ C++ (GCC) | 54 |
π Ruby | 72 |
| πΉ Go | 60 |
π HTML/CSS | 82 |
[!TIP] For a complete list of 60+ supported languages, query your Judge0 instance:
GET /languages
π‘οΈ Error Handling
The server is engineered to never crash from tool-level errors. Every failure is caught and returned gracefully:
| Scenario | Behavior |
|---|---|
| π Codebox timeout / network error | Error details in text response; screenshot still attempted |
| π₯οΈ Playwright crash | Codebox results returned with rendering error note |
| π₯ Both fail | Descriptive error text returned; no image block |
β οΈ Missing CODEBOX_URL |
Codebox phase skipped with warning; rendering proceeds |
π§° Development
# Build and run in one step
npm run dev
# Watch mode with tsx (great for iterating)
npx tsx watch src/index.ts
Project Structure
visual-loop-mcp/
βββ π src/
β βββ index.ts # Main server β Codebox + Playwright + MCP
βββ π build/ # Compiled JavaScript output
βββ π¦ package.json # Dependencies & scripts
βββ βοΈ tsconfig.json # TypeScript configuration
βββ π README.md # You are here!
π οΈ Tech Stack
<div align="center">
| Technology | Role |
|---|---|
| <img src="https://img.shields.io/badge/-TypeScript-3178C6?logo=typescript&logoColor=white&style=for-the-badge" height="28" /> | Core language with strict type safety |
| <img src="https://img.shields.io/badge/-MCP%20SDK-6C63FF?style=for-the-badge" height="28" /> | Model Context Protocol server framework |
| <img src="https://img.shields.io/badge/-Playwright-2EAD33?logo=playwright&logoColor=white&style=for-the-badge" height="28" /> | Headless browser automation & screenshots |
| <img src="https://img.shields.io/badge/-Judge0-E34F26?style=for-the-badge" height="28" /> | Sandboxed multi-language code execution |
| <img src="https://img.shields.io/badge/-Axios-5A29E4?logo=axios&logoColor=white&style=for-the-badge" height="28" /> | HTTP client for Codebox API |
| <img src="https://img.shields.io/badge/-Zod-3E67B1?logo=zod&logoColor=white&style=for-the-badge" height="28" /> | Runtime schema validation |
</div>
π€ Contributing
Contributions are welcome! Here's how to get started:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
π License
This project is licensed under the MIT License β see the LICENSE file for details.
<div align="center">
<img src="https://capsule-render.vercel.app/api?type=waving&color=0:6C63FF,50:A855F7,100:EC4899&height=120§ion=footer&animation=fadeIn" width="100%" alt="Footer"/>
<br/>
Built with β€οΈ by Iqbal
<br/>
<a href="https://github.com/IqbalHere/-Visual-Loop-MCP-Server/stargazers"> <img src="https://img.shields.io/github/stars/IqbalHere/-Visual-Loop-MCP-Server?style=social" alt="GitHub Stars" /> </a> Β Β <a href="https://github.com/IqbalHere/-Visual-Loop-MCP-Server/network/members"> <img src="https://img.shields.io/github/forks/IqbalHere/-Visual-Loop-MCP-Server?style=social" alt="GitHub Forks" /> </a> Β Β <a href="https://github.com/IqbalHere/-Visual-Loop-MCP-Server/issues"> <img src="https://img.shields.io/github/issues/IqbalHere/-Visual-Loop-MCP-Server?style=social" alt="GitHub Issues" /> </a>
<br/><br/>
β Star this repo if you found it useful! β
</div>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.