MCP server for PromptArchitect Prompt Lab - AI-powered prompt engineering with workspace-aware refinement.
npm install @merabylabs/promptarchitect-mcprefine_prompt | Improve your current prompt based on feedback and your workspace context |
analyze_prompt | Evaluate prompt quality with scores and improvement suggestions |
generate_prompt | Transform a raw idea into a well-structured prompt tailored to your project |
set_auto_refine | Enable/disable automatic prompt refinement on every chat |
get_auto_refine_status | Check current auto-refine settings |
You: enable auto-refine
AI: ✅ Auto-refine enabled. All prompts will now be automatically refined.
You: help me debug my React component
AI: [Automatically refines prompt to be more specific, then helps you]
`
How it works:
1. Say "enable auto-refine" or use the set_auto_refine tool
2. Every subsequent prompt is automatically refined with your project context
3. The AI uses the improved prompt to give you better responses
4. Say "disable auto-refine" to turn it off
This is perfect for developers who want consistently high-quality prompts without extra effort.
$3
- Template Library: Reference templates for coding, writing, research, and analysis tasks
- Category Collections: Browse templates by category for inspiration
Installation
`bash
npm install @merabylabs/promptarchitect-mcp
`
Or install globally:
`bash
npm install -g @merabylabs/promptarchitect-mcp
`
Usage
PromptArchitect MCP server works with any IDE or application that supports the Model Context Protocol. Below are configuration examples for popular editors.
> No API key required! The MCP server uses the PromptArchitect backend API, so you don't need your own Gemini API key.
---
$3
Add to your Claude Desktop configuration file:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
`json
{
"mcpServers": {
"promptarchitect": {
"command": "npx",
"args": ["@merabylabs/promptarchitect-mcp"]
}
}
}
`
---
$3
Add to your VS Code settings.json (Cmd/Ctrl+Shift+P → "Preferences: Open Settings (JSON)"):
`json
{
"github.copilot.chat.mcp.servers": {
"promptarchitect": {
"command": "npx",
"args": ["@merabylabs/promptarchitect-mcp"]
}
}
}
`
---
$3
Add to your Cursor MCP settings:
- macOS/Linux: ~/.cursor/mcp.json
- Windows: %USERPROFILE%\.cursor\mcp.json
- Or via: Settings → MCP
`json
{
"mcpServers": {
"promptarchitect": {
"command": "npx",
"args": ["@merabylabs/promptarchitect-mcp"]
}
}
}
`
📖 Cursor MCP Documentation
---
$3
Add to your Windsurf MCP configuration:
- macOS/Linux: ~/.codeium/windsurf/mcp_config.json
- Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
`json
{
"mcpServers": {
"promptarchitect": {
"command": "npx",
"args": ["@merabylabs/promptarchitect-mcp"]
}
}
}
`
📖 Windsurf MCP Documentation
---
$3
Add to your Zed settings:
- macOS: ~/.config/zed/settings.json
- Linux: ~/.config/zed/settings.json
`json
{
"context_servers": {
"promptarchitect": {
"command": {
"path": "npx",
"args": ["@merabylabs/promptarchitect-mcp"]
},
"settings": {}
}
}
}
`
📖 Zed MCP Documentation
---
$3
Works with IntelliJ IDEA, PyCharm, WebStorm, PhpStorm, GoLand, RubyMine, CLion, DataGrip, Rider, Android Studio.
1. Install the MCP Client plugin from JetBrains Marketplace
2. Go to Settings → Tools → MCP Servers
3. Add a new server with this configuration:
`json
{
"mcpServers": {
"promptarchitect": {
"command": "npx",
"args": ["@merabylabs/promptarchitect-mcp"]
}
}
}
`
Or add to .idea/mcp.json in your project.
📖 JetBrains MCP Plugin
---
$3
Add to your Continue configuration:
- Global: ~/.continue/config.json
- Project: .continue/config.json
`json
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "npx",
"args": ["@merabylabs/promptarchitect-mcp"]
}
}
]
}
}
`
📖 Continue MCP Documentation
---
$3
Open Cline Settings → MCP Servers, or edit cline_mcp_settings.json:
`json
{
"mcpServers": {
"promptarchitect": {
"command": "npx",
"args": ["@merabylabs/promptarchitect-mcp"],
"disabled": false
}
}
}
`
📖 Cline MCP Documentation
---
$3
Any application supporting MCP can use this server. The standard configuration is:
| Property | Value |
|----------|-------|
| Command | npx |
| Args | ["@merabylabs/promptarchitect-mcp"] |
For global installation, use promptarchitect-mcp as the command after running:
`bash
npm install -g @merabylabs/promptarchitect-mcp
`
---
$3
`typescript
import { refinePrompt, analyzePrompt } from '@promptarchitect/mcp-server';
// Refine an existing prompt
const result = await refinePrompt({
prompt: 'Write code to sort an array',
feedback: 'Make it more specific about language and edge cases',
});
console.log(result.refinedPrompt);
// => "Write a TypeScript function that sorts an array of numbers..."
// Analyze prompt quality
const analysis = await analyzePrompt({
prompt: 'Help me with my code',
});
console.log(analysis.scores); // { overall: 45, clarity: 50, ... }
console.log(analysis.suggestions); // ["Be more specific about...", ...]
`
Configuration
$3
| Variable | Required | Description |
|----------|----------|-------------|
| LOG_LEVEL | No | Logging level: debug, info, warn, error. Default: info |
Tool Reference
$3
Improve an existing prompt based on feedback. This is the primary tool.
Input:
`json
{
"prompt": "Write code",
"feedback": "Make it more specific and add examples",
"preserveStructure": true
}
`
Output:
`json
{
"refinedPrompt": "Write a TypeScript function that...",
"changes": ["Added specificity", "Included example"],
"metadata": {
"originalWordCount": 2,
"refinedWordCount": 45
}
}
`
$3
Evaluate prompt quality and get improvement suggestions.
Input:
`json
{
"prompt": "You are a helpful assistant. Help me write code."
}
`
Output:
`json
{
"scores": {
"overall": 65,
"clarity": 70,
"specificity": 50,
"structure": 60,
"actionability": 80
},
"suggestions": [
"Add more specific details about the code",
"Include examples of expected output"
],
"strengths": ["Clear action verb"],
"weaknesses": ["Lacks specificity"]
}
`
$3
Transform a raw idea into a well-structured prompt.
Input:
`json
{
"idea": "Create a code review assistant",
"template": "coding",
"context": "For TypeScript projects"
}
`
Output:
`json
{
"prompt": "You are a senior code reviewer...",
"metadata": {
"template": "coding",
"wordCount": 150,
"hasStructure": true
}
}
`
Development
$3
`bash
npm install
npm run build
`
$3
`bash
npm test
`
$3
`bash
npm start
`
Architecture
`
mcp-server/
├── src/
│ ├── tools/ # MCP tools (refine, analyze, generate)
│ ├── resources/ # Template library for reference
│ ├── utils/ # Gemini client, logger
│ ├── server.ts # MCP server configuration
│ ├── cli.ts # CLI entry point
│ └── index.ts # Main exports
└── examples/ # Configuration examples
``