Buildez MCP Server
OfficialIntegrates with Windsurf (by Codeium) to generate websites from descriptions through Buildez.ai.
Allows AI agents to create complete websites using Buildez.ai through GitHub Copilot's MCP support.
Click on "Deploy 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., "@Buildez MCP ServerBuild a website for my bakery, Sweet Treats"
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.
Buildez MCP Server
Build complete websites using AI through any MCP-compatible tool.
What is this?
This MCP server connects AI assistants to Buildez.ai, allowing you to create full websites just by describing what you want.
Example:
"Build me a website for Tony's Pizzeria - a family Italian restaurant in Brooklyn with online ordering"
And it will create a complete, live website for you.
Related MCP server: Magic Patterns MCP Server
Supported Tools
Tool | Status |
✅ Supported | |
✅ Supported | |
✅ Supported | |
✅ Supported | |
✅ Supported | |
✅ Supported |
Installation
Step 1: Install Node.js (Required)
Windows
Go to nodejs.org/en/download
Click the "Windows Installer (.msi)" button
Run the downloaded file
Click Next → Next → Next → Install
Restart your computer (or at least close and reopen Command Prompt)
Mac
brew install nodeOr download from nodejs.org
Linux
sudo apt install nodejs npmStep 2: Install Buildez MCP
Open Command Prompt (Windows) or Terminal (Mac/Linux) and run:
npm install -g buildez-mcpWindows tip: Press Win + R, type cmd, press Enter to open Command Prompt.
Step 3: Verify Installation
buildez-mcp --helpIf you see output (not an error), it's installed correctly.
Setup by Tool
VS Code (GitHub Copilot)
VS Code now supports MCP servers with GitHub Copilot.
Option 1: User Settings (All Projects)
Open VS Code
Press
Ctrl+Shift+P(Windows/Linux) orCmd+Shift+P(Mac)Type "Preferences: Open User Settings (JSON)" and press Enter
Add this to your settings:
{
"mcp": {
"servers": {
"buildez": {
"command": "npx",
"args": ["buildez-mcp"],
"env": {
"BUILDEZ_API_URL": "https://buildez.ai"
}
}
}
}
}Option 2: Workspace Settings (Single Project)
Create a file .vscode/mcp.json in your project:
{
"servers": {
"buildez": {
"command": "npx",
"args": ["buildez-mcp"],
"env": {
"BUILDEZ_API_URL": "https://buildez.ai"
}
}
}
}Restart VS Code
Open Copilot Chat and ask: "Build a website for my coffee shop"
Note: Requires GitHub Copilot subscription and VS Code 1.99+
Cursor IDE
Windows
Edit file: C:\Users\YOUR_USERNAME\.cursor\mcp.json
{
"mcpServers": {
"buildez": {
"command": "npx",
"args": ["buildez-mcp"],
"env": {
"BUILDEZ_API_URL": "https://buildez.ai"
}
}
}
}Mac / Linux
Edit file: ~/.cursor/mcp.json
{
"mcpServers": {
"buildez": {
"command": "npx",
"args": ["buildez-mcp"],
"env": {
"BUILDEZ_API_URL": "https://buildez.ai"
}
}
}
}Then restart Cursor.
Claude Desktop
Windows
Edit file: C:\Users\YOUR_USERNAME\AppData\Roaming\Claude\claude_desktop_config.json
{
"mcpServers": {
"buildez": {
"command": "npx",
"args": ["buildez-mcp"],
"env": {
"BUILDEZ_API_URL": "https://buildez.ai"
}
}
}
}Mac
Edit file: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"buildez": {
"command": "npx",
"args": ["buildez-mcp"],
"env": {
"BUILDEZ_API_URL": "https://buildez.ai"
}
}
}
}Then restart Claude Desktop.
Claude Code (CLI)
Claude Code has built-in MCP support. Just run this command:
claude mcp add buildez-mcp -- npx buildez-mcpVerify it was added:
claude mcp listTo use it, just start Claude Code and ask:
"Build a website for my coffee shop called Bean Dreams"Cline (VS Code Extension)
Install Cline extension in VS Code
Open Cline settings
Go to MCP Servers section
Add:
{
"buildez": {
"command": "npx",
"args": ["buildez-mcp"],
"env": {
"BUILDEZ_API_URL": "https://buildez.ai"
}
}
}Windsurf
Edit your Windsurf MCP config and add:
{
"mcpServers": {
"buildez": {
"command": "npx",
"args": ["buildez-mcp"],
"env": {
"BUILDEZ_API_URL": "https://buildez.ai"
}
}
}
}Usage
After setup, just ask the AI to build a website:
Examples:
"Build a website for a coffee shop called Morning Brew in Seattle"
"Create a portfolio website for a photographer named Sarah"
"Build an e-commerce site for a jewelry store"
"Make a website for a law firm specializing in family law"
The AI will:
Analyze your requirements
Select the best components (170+ available)
Generate custom content for your business
Deploy the website
Give you the live URL
Available Tool
Tool | Description |
| Create a complete website from a business name and description |
Example Output
✅ Website "Tony's Pizzeria" created successfully!
Live URL: https://webid.is/tonys-pizzeria-x7k2m9
Editor: https://buildez.ai/editor/tonys-pizzeria-x7k2m9
Components used:
- Hero section with restaurant branding
- Menu display
- Contact information
- Online ordering
- Testimonials
- Footer with location mapTroubleshooting
Windows: "npm is not recognized"
Node.js is not installed or not in PATH
Reinstall Node.js from nodejs.org/en/download
Make sure to restart Command Prompt after installing
Windows: "buildez-mcp is not recognized"
Run
npm install -g buildez-mcpagainTry using full path:
%APPDATA%\npm\buildez-mcp
MCP shows "Error" or red dot
Restart your IDE/app
Check that BUILDEZ_API_URL is set to
https://buildez.ai
Website not generating
Check internet connection
Try a simpler description first
Links
Website: buildez.ai
Documentation: buildez.ai/docs
Support: support@buildez.ai
License
MIT
Available Tools
1 toolbuild_websiteA
Build and deploy a complete website instantly. When user wants a website, ask ONLY two questions: 1) Business name? 2) Brief description of the business? Then immediately call this tool. Do not ask about colors, style, framework, or technology - the AI handles everything automatically.
| Name | Required | Description | Default |
|---|---|---|---|
| description | Yes | Brief description of what the business does | |
| businessName | Yes | Business name |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses that deployment happens automatically and that the AI handles design and technology choices unprompted, but says nothing about deployment target, hosting, permissions or credentials required, cost, reversibility, or latency beyond 'instantly'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The core action is front-loaded in the first sentence, followed by the interaction protocol. It is a bit instruction-heavy with the enumerated questions, but every sentence carries operational value and nothing is redundant.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema and no annotations, so the description should say more about what comes back (a URL? a preview? hosting details?) and what the agent should do with the result. The input-side workflow is well covered, but the post-call picture is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so both parameters (businessName, description) are already documented. The description reinforces that these are the only two inputs and that they should be elicited from the user, but adds no format, length, or constraint details beyond the schema. Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb and resource with scope modifiers: 'Build and deploy a complete website instantly.' An agent immediately knows this produces a finished, deployed site rather than scaffolding or advice. No siblings exist, so no differentiation is needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states the trigger condition ('When user wants a website') and prescribes the exact interaction protocol: ask only two questions, then call the tool immediately. It also explicitly rules out asking about colors, style, framework, or technology, which is genuine when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.2.3- First observed
build_website
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of confusing it with another tool. Its stated purpose is clear and singular: build and deploy a complete website.
The single tool name follows a clear snake_case verb_noun pattern (build_website). With only one tool, there is no inconsistency to assess.
A one-tool server is borderline thin for a website-building domain, even though the tool itself is broad and handles a complete generation flow. Additional tools for updates, status, or retrieval could make the surface more practical.
The tool covers initial creation and deployment, but there is no way to update, delete, list, or check the status of an existing website. These are notable lifecycle gaps for an MCP server centered on website building.
Maintenance
Related MCP Connectors
Build and publish websites through AI conversation.
Build, edit, and publish real websites and online stores by chatting with your AI assistant.
Give any MCP-compatible AI assistant a builder for live, hosted web tools and workflows.
Enables AI assistants to natively interact with the Serpzilla link-building marketplace.
Related MCP Servers
- AlicenseCqualityCmaintenanceEnables AI assistants to manage WordPress content, design, SEO, WooCommerce, and more through natural language commands.10013 npm3MIT
- AlicenseNot gradedqualityFmaintenanceEnables AI assistants to generate UI components and web interfaces from natural language descriptions using the Magic Patterns API.6 npm4MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to extract design systems, brand guidelines, copy, and sitemap structure from any live website via the Pastebase API.MIT
- AlicenseAqualityAmaintenanceBridges AI assistants to WebCake, enabling users to build, validate, and save editable landing pages from natural language descriptions.2371 npm5MIT