@merabylabs/meraby-ai-mcp

Meraby AI MCP Server — Your tireless background guardian for AI-powered development

A Model Context Protocol (MCP) server that provides autonomous coding capabilities powered by Vertex AI with Gemini. Part of the Meraby Daemon ecosystem — Watch, Plan, Execute.

Works with: Claude Desktop • VS Code (Copilot) • Cursor • Windsurf • Zed • JetBrains IDEs • Continue.dev • Cline

🔗 Part of the Meraby Daemon Ecosystem

| Product | Description | |---------|-------------| | Meraby AI MCP | This package — MCP server for IDE integration | | VS Code Extension | Full Daemon panel with autonomous agent capabilities | | Web App | Full-featured web application |

✨ Why Meraby AI MCP?

🎯 Workspace-Aware Intelligence

Unlike generic AI tools, Meraby AI understands your project context. When executing tasks, it considers:

• Your tech stack — React, Node, Python, or whatever you're building with
• Project structure — File organization, naming conventions, architecture patterns
• Dependencies — Libraries and frameworks from your package.json/requirements.txt
• Your original request — Ensures actions stay aligned with your actual goal

This means AI assistance tailored to your specific codebase, not generic boilerplate.

🚀 Key Benefits

• No API key required — Powered by Vertex AI with Gemini
• Works in your IDE — Integrates with your existing workflow via MCP
• Context-aware — Actions that understand your project conventions
• Autonomous execution — Plan and execute multi-step tasks

Features

🛠️ Tools

| Tool | Description | |------|-------------| | prompt | Generate, refine, analyze prompts, or run workflows | | read_file | Read file contents from the workspace | | write_file | Create or update files | | list_files | List directory contents (glob filters, respects .gitignore) | | search | Text or semantic search across files (auto-index for semantic) | | search_and_replace | Make targeted edits across files | | get_workspace_context | Get project structure and tech stack | | symbols | Symbol overview, lookup, references, edits, and AST structure | | execute_command | Run shell commands | | run_in_terminal | NEW Execute commands in VS Code integrated terminal | | quick_command | NEW Run quick commands with automatic tool selection | | run_npm_script | Execute npm scripts | | git_command | Git operations | | install_dependencies | Install packages | | custom_workflow | Custom automation workflows |

📦 Resources

• Template Library: Reference templates for coding, writing, research, and analysis tasks
• Category Collections: Browse templates by category for inspiration

Installation

npm install @merabylabs/meraby-ai-mcp

Or install globally:

npm install -g @merabylabs/meraby-ai-mcp

Usage

Meraby AI 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 Vertex AI, so you don't need your own Gemini API key.

Claude Desktop

Add to your Claude Desktop configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "meraby-ai": {
      "command": "npx",
      "args": ["@merabylabs/meraby-ai-mcp"]
    }
  }
}

VS Code (GitHub Copilot)

Add to your VS Code settings.json (Cmd/Ctrl+Shift+P → "Preferences: Open Settings (JSON)"):

{
  "github.copilot.chat.mcp.servers": {
    "meraby-ai": {
      "command": "npx",
      "args": ["@merabylabs/meraby-ai-mcp"]
    }
  }
}

Cursor

Add to your Cursor MCP settings:

• macOS/Linux: ~/.cursor/mcp.json
• Windows: %USERPROFILE%\.cursor\mcp.json
• Or via: Settings → MCP

{
  "mcpServers": {
    "meraby-ai": {
      "command": "npx",
      "args": ["@merabylabs/meraby-ai-mcp"]
    }
  }
}

📖 Cursor MCP Documentation

Windsurf (Codeium)

Add to your Windsurf MCP configuration:

• macOS/Linux: ~/.codeium/windsurf/mcp_config.json
• Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

{
  "mcpServers": {
    "meraby-ai": {
      "command": "npx",
      "args": ["@merabylabs/meraby-ai-mcp"]
    }
  }
}

📖 Windsurf MCP Documentation

Zed

Add to your Zed settings:

• macOS: ~/.config/zed/settings.json
• Linux: ~/.config/zed/settings.json

{
  "context_servers": {
    "meraby-ai": {
      "command": {
        "path": "npx",
        "args": ["@merabylabs/meraby-ai-mcp"]
      },
      "settings": {}
    }
  }
}

📖 Zed MCP Documentation

JetBrains IDEs

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:

{
  "mcpServers": {
    "meraby-ai": {
      "command": "npx",
      "args": ["@merabylabs/meraby-ai-mcp"]
    }
  }
}

Or add to .idea/mcp.json in your project.

📖 JetBrains MCP Plugin

Continue.dev

Add to your Continue configuration:

• Global: ~/.continue/config.json
• Project: .continue/config.json

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "npx",
          "args": ["@merabylabs/meraby-ai-mcp"]
        }
      }
    ]
  }
}

📖 Continue MCP Documentation

Cline

Add to your Cline MCP settings in VS Code:

{
  "cline.mcp.servers": {
    "meraby-ai": {
      "command": "npx",
      "args": ["@merabylabs/meraby-ai-mcp"]
    }
  }
}

📖 Cline MCP Documentation

🔧 Configuration

Environment Variables

# For local development with API key fallback
GEMINI_API_KEY=your-key-here

# For Vertex AI (production) - auto-detected in Google Cloud
GCLOUD_PROJECT=your-project-id
GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json

Programmatic Usage

import { createServer } from '@merabylabs/meraby-ai-mcp';

const server = createServer();
// ... connect to your transport

📊 How It Works

┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐
│   Your IDE      │────▶│  MCP Protocol   │────▶│   Meraby AI     │
│  (Claude, etc)  │◀────│   (stdio/SSE)   │◀────│   MCP Server    │
└─────────────────┘     └─────────────────┘     └────────┬────────┘
                                                         │
                                                         ▼
                                              ┌─────────────────┐
                                              │   Vertex AI     │
                                              │     Gemini      │
                                              └─────────────────┘

The MCP server:

1. Receives tool calls from your IDE
2. Executes workspace operations (read/write/search)
3. Calls Vertex AI for intelligent processing
4. Returns results via MCP protocol

🔒 Security

• No data storage: Your code never leaves your machine (except for AI processing)
• Vertex AI: Enterprise-grade security with IAM authentication
• Local execution: All file operations happen locally
• Audit logging: Full visibility in Google Cloud Console

📝 License

MIT License - see LICENSE for details.

🔗 Links

• Meraby Labs
• VS Code Extension
• GitHub
• Model Context Protocol

Built with 🔮 by Meraby Labs