live-preview-mcp
Allows starting and managing live previews of Angular applications through framework auto-detection.
Provides integration with Cloudflare tunnels to expose live previews via public URLs.
Enables running application previews in Docker containers with security hardening.
Allows starting and managing live previews of Expo projects through framework auto-detection.
Allows starting and managing live previews of Express applications through framework auto-detection.
Allows starting and managing live previews of Flutter projects through framework auto-detection.
Allows starting and managing live previews of Next.js projects through framework auto-detection.
Provides integration with ngrok tunnels to expose live previews via public URLs.
Allows starting and managing live previews of Vite projects through framework auto-detection.
Click on "Install 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., "@live-preview-mcpStart a live preview for my app and share the URL"
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.
Live Preview MCP Server
Version 1.1 (post red-team hardening) — Production-grade Model Context Protocol server that lets any MCP-capable AI assistant start, manage, and embed live application previews in an iframe.
Security Hardening (v1.1)
No shell injection: Docker and process spawn always use argument arrays (
shell: false).Safe environment: Only an explicit allow-list of env vars is passed; dangerous keys (
NODE_OPTIONS,LD_PRELOAD, etc.) are stripped.Symlink-safe path checks:
realpathSyncbefore allow-list validation.WebSocket rate limiting + per-preview connection caps.
Process-liveness readiness: readiness probe also verifies the child process is still alive.
Concurrent preview limit (default 10).
Docker:
CapDrop: ALL,no-new-privileges, non-root user where possible, AutoRemove + startup orphan reaper.Stronger log redaction (JWT, AWS keys, GitHub/Slack/OpenAI tokens, etc.).
Token length increased to 32 random bytes.
Related MCP server: Streamable Pod Shell MCP Server
Features
MCP Tools:
start_preview,stop_preview,get_preview_status,get_preview_logs,list_previews,reload_preview,update_preview_config,share_preview,get_mobile_qr,set_auth_tokenFramework Auto-Detection: Vite, Next.js, CRA, Vue, Angular, Express, static, Expo, Flutter
HTTP Dashboard + Reverse Proxy with framing headers removed
Optional Docker, Cloudflare/ngrok tunnels, mobile QR, token auth, Cloud-IDE awareness
Requirements
Node.js ≥ 18
Optional: Docker,
cloudflared,ngrok
Install & Build
cd live-preview-mcp
npm install
npm run buildRun
node dist/index.jsMCP Client Configuration
{
"mcpServers": {
"live-preview": {
"command": "node",
"args": ["/absolute/path/to/live-preview-mcp/dist/index.js"],
"env": {
"PORT": "9000",
"ALLOWED_DIRS": "/path/to/projects"
}
}
}
}License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Your AI Agent's Infrastructure Layer. Connect Claude, Copilot, Codex, or ChatGPT to 200+ managed open source services. Start databases, pipelines, and applications through natural language.
Host apps built with AI: deploy to a live HTTPS URL, custom domains, secrets and backups.
Deploy and manage your apps, databases, storage, and scheduled jobs from your AI agent
Deploy and host the apps your AI assistant builds — a real server, database, and shareable URL.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables AI assistants to securely execute Python and JavaScript code in sandboxed environments, with file management and package installation.788-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to create isolated Kubernetes Pod sessions for real-time shell command execution, file management, and Node.js code execution, with automatic TTL-based cleanup.MIT
- AlicenseAqualityCmaintenanceConnects AI tools to local dev servers, enabling them to view pages, call APIs, read/edit files, and run commands with safety guardrails.13MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to execute code in isolated sandboxes with support for Python, JavaScript, and TypeScript, featuring intelligent caching and semantic search for code reuse.9MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/copperlang2007/live-preview-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server