Sponsored by Deepsite.site

Previewship Mcp

Created By
blockdancez4 months ago
PreviewShip MCP lets Claude Code, Cursor, Windsurf, Codex-compatible workflows, and other MCP clients publish browser-ready frontend artifacts without opening a hosting dashboard. It can deploy a built dist/build/out/public folder, a single HTML file, Markdown, or an AI-generated HTML artifact, then return a stable PreviewShip preview URL for review, sharing, QA, or client feedback. PreviewShip hosts static output only; framework source folders should be built first.
Overview

PreviewShip

Deploy previews, share instantly. From your editor, terminal, AI agent, or browser — one step to a live link.

PreviewShip is a frontend preview deployment and sharing platform for developers. Deploy your static site and get a shareable preview URL in seconds — no Git, no CI/CD, no complex configuration.

Open Source Packages

PreviewShip provides three open-source client packages:

PackagenpmDescription
CLIpreviewshipDeploy from the terminal with one command
MCP Serverpreviewship-mcpNative tool integration for AI coding agents
VS Code ExtensionMarketplaceOne-click deploy from your editor

Deployment Methods

MethodCommand / ActionBest For
CLInpx previewship deploy ./distTerminal, scripts, CI/CD
MCP ServerSay "deploy to PreviewShip" in AI chatClaude Code, Cursor, Windsurf
VS Code / Cursor ExtensionCommand Palette → PreviewShip: DeployEditor-first workflow
Web ConsoleDrag & drop zip at previewship.comZero-tool deployment

CLI

One-command deploy from any terminal. Supports JSON output for AI agents and CI pipelines.

Quick Start

# Set your API Key
npx previewship login --key ps_live_YOUR_KEY

# Deploy a directory
npx previewship deploy ./dist

Commands

CommandDescription
previewship login [--key KEY]Set API Key for authentication
previewship deploy [path] [-n name] [--json]Deploy a directory and get a preview URL
previewship status <id> [--json]Check deployment status by ID
previewship usage [--json]Show remaining deployment quota
previewship whoamiDisplay current configuration

Options

# Deploy with a custom project name
npx previewship deploy ./dist -n my-project

# JSON output for AI agents and CI
npx previewship deploy ./dist --json

# Custom exclude patterns
npx previewship deploy ./dist --exclude "*.map" --exclude "tests/**"

Environment Variables

VariableDescription
PREVIEWSHIP_API_KEYAPI Key (overrides saved config)
PREVIEWSHIP_SERVER_URLCustom API server URL
CIAuto-enables JSON output in CI environments
NO_COLORDisables colored output

Programmatic Usage

The CLI also exports its core functions for use as a library:

import { deploy, getStatus, getUsage } from 'previewship'
import { ApiClient } from 'previewship'
import { packDirectory, DEFAULT_EXCLUDE_PATTERNS } from 'previewship'

MCP Server

Model Context Protocol server that lets AI coding agents deploy previews as a native tool call. Works with Claude Code, Cursor, Windsurf, and any MCP-compatible client.

Setup

Claude Code — add to ~/.claude/settings.json:

{
  "mcpServers": {
    "previewship": {
      "command": "npx",
      "args": ["-y", "previewship-mcp"],
      "env": {
        "PREVIEWSHIP_API_KEY": "ps_live_YOUR_KEY"
      }
    }
  }
}

Cursor — create .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "previewship": {
      "command": "npx",
      "args": ["-y", "previewship-mcp"],
      "env": {
        "PREVIEWSHIP_API_KEY": "ps_live_YOUR_KEY"
      }
    }
  }
}

Windsurf — add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "previewship": {
      "command": "npx",
      "args": ["-y", "previewship-mcp"],
      "env": {
        "PREVIEWSHIP_API_KEY": "ps_live_YOUR_KEY"
      }
    }
  }
}

Available Tools

ToolDescriptionParameters
deploy_previewDeploy a directory and get a preview URLpath (optional), projectName (optional), excludePatterns (optional)
check_deploymentCheck deployment status by IDdeploymentId (required)
show_usageShow remaining deployment quota

Usage

Once configured, simply ask your AI agent:

"Deploy this project to PreviewShip" "Check the status of my last deployment" "How many deploys do I have left today?"


VS Code / Cursor Extension

One-click deploy from VS Code or Cursor. Install from the VS Code Marketplace or Open VSX Registry.

Install

Via Command Palette (Ctrl+P / Cmd+P):

ext install previewship.previewship

Via VSIX (offline install):

code --install-extension previewship-0.1.3.vsix
# Or for Cursor:
cursor --install-extension previewship-0.1.3.vsix

Commands

CommandDescription
PreviewShip: Set API KeyStore your API Key securely (encrypted via VS Code Secrets API)
PreviewShip: Deploy Current WorkspacePackage, upload, and deploy your project
PreviewShip: Show UsageDisplay daily/monthly deployment quota

Settings

SettingDefaultDescription
previewship.serverUrlhttps://api.previewship.comAPI server URL
previewship.excludePatternsnode_modules/**, .git/**, .env*, etc.File exclude patterns for packaging
previewship.pollIntervalMs3000Deployment status polling interval (ms)
previewship.pollTimeoutMs300000Polling timeout (ms)

Getting Started

  1. Register a free account at previewship.com
  2. Create an API Key from the console → API Keys page
  3. Deploy using any method above
  4. Share the preview link with your team

Plans

FreePro MonthlyPro Yearly
Price$0$9/mo$84/yr ($7/mo)
Projects1812
Daily Deploys52035
Max Zip Size15 MB50 MB80 MB
Preview Expiry7 days30 days365 days

Free plan requires no credit card. Start deploying instantly.

Supported Frameworks

Any static frontend output works — React, Vue, Svelte, Angular, Next.js (export), Nuxt (generate), Astro, vanilla HTML/CSS/JS, and more. Just make sure your build output contains an index.html.

Requirements

  • Node.js ≥ 20.0.0 (for CLI and MCP)
  • VS Code ≥ 1.85.0 (for extension)
  • An API Key from previewship.com

License

MIT — see LICENSE for details.

Server Config

{
  "mcpServers": {
    "previewship": {
      "command": "npx",
      "args": [
        "-y",
        "previewship-mcp"
      ],
      "env": {
        "PREVIEWSHIP_API_KEY": "ps_live_your_key_here"
      }
    }
  }
}
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
Amap Maps高德地图官方 MCP Server
CursorThe AI Code Editor
WindsurfThe new purpose-built IDE to harness magic
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Playwright McpPlaywright MCP server
ChatWiseThe second fastest AI chatbot™
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
RedisA Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
Serper MCP ServerA Serper MCP Server
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。
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
DeepChatYour AI Partner on Desktop
Tavily Mcp
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs