Skip to main content

Client Configuration

This document describes how to configure the Lovrabet MCP server in various AI editors and development environments.

Standard Configuration​

{
  "mcpServers": {
    "lovrabet-dataset": {
      "command": "npx",
      "args": ["-y", "@lovrabet/dataset-mcp-server"],
      "env": {
        "LOVRABET_APP_CODE": "your-app-code"
      }
    }
  }
}

Configuration Parameters​

ParameterRequiredDescription
LOVRABET_APP_CODEYesYour Lovrabet application AppCode
LOVRABET_ENVNoEnvironment: online (default) or daily
MCP_DEBUGNoSet to 1 to enable verbose logging

MCP Client Configuration​

Amp​

Visit https://ampcode.com/manual#mcp and use the standard config above. You can also install using the CLI:

amp mcp add lovrabet-dataset -- npx -y @lovrabet/dataset-mcp-server

Antigravity​

Visit https://antigravity.google/docs/mcp to install a custom MCP server. Add the following config:

{
  "mcpServers": {
    "lovrabet-dataset": {
      "command": "npx",
      "args": ["-y", "@lovrabet/dataset-mcp-server"],
      "env": {
        "LOVRABET_APP_CODE": "your-app-code"
      }
    }
  }
}

Claude Code​

Use the Claude Code CLI to add the Lovrabet MCP server:

claude mcp add lovrabet-dataset --scope user npx -y @lovrabet/dataset-mcp-server

Or manually edit ~/.claude/settings.json:

{
  "mcpServers": {
    "lovrabet-dataset": {
      "command": "npx",
      "args": ["-y", "@lovrabet/dataset-mcp-server"],
      "env": {
        "LOVRABET_APP_CODE": "your-app-code"
      }
    }
  }
}

Claude Desktop​

Edit the config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "lovrabet-dataset": {
      "command": "npx",
      "args": ["-y", "@lovrabet/dataset-mcp-server"],
      "env": {
        "LOVRABET_APP_CODE": "your-app-code"
      }
    }
  }
}

Cline​

Visit https://docs.cline.bot/mcp/configuring-mcp-servers and use the standard config above.

Codex​

Follow the MCP configure guide using the standard config. You can also install using the Codex CLI:

codex mcp add lovrabet-dataset -- npx -y @lovrabet/dataset-mcp-server

On Windows 11

Configure in .codex/config.toml:

[mcp_servers.lovrabet-dataset]
command = "cmd"
args = [
    "/c",
    "npx",
    "-y",
    "@lovrabet/dataset-mcp-server",
]
env = { LOVRABET_APP_CODE = "your-app-code" }
startup_timeout_ms = 20_000

Copilot CLI​

Start Copilot CLI and run:

/mcp add

Configure the following fields and press CTRL+S to save:

  • Server name: lovrabet-dataset
  • Server Type: [1] Local
  • Command: npx -y @lovrabet/dataset-mcp-server
  • Environment Variables: LOVRABET_APP_CODE=your-app-code

Copilot / VS Code​

Use the VS Code CLI:

code --add-mcp '{"name":"io.lovrabet.dataset-mcp-server","command":"npx","args":["-y","@lovrabet/dataset-mcp-server"],"env":{"LOVRABET_APP_CODE":"your-app-code"}}'

Or manually follow the MCP install guide.

Cursor​

Go to Cursor Settings -> MCP -> New MCP Server. Use the standard config above.

Factory CLI​

Use the Factory CLI:

droid mcp add lovrabet-dataset "npx -y @lovrabet/dataset-mcp-server"

Gemini CLI​

Project wide:

gemini mcp add lovrabet-dataset npx -y @lovrabet/dataset-mcp-server

Globally:

gemini mcp add -s user lovrabet-dataset npx -y @lovrabet/dataset-mcp-server

Gemini Code Assist​

Follow the MCP configure guide using the standard config.

JetBrains AI Assistant & Junie​

Go to Settings | Tools | AI Assistant | Model Context Protocol (MCP) -> Add. Use the standard config. For JetBrains Junie, configure in Settings | Tools | Junie | MCP Settings -> Add.

Kiro​

In Kiro Settings, go to Configure MCP > Open Workspace or User MCP Config > Use the standard config.

Or, from the IDE Activity Bar > Kiro > MCP Servers > Click Open MCP Config. Use the standard config.

OpenCode​

Add to ~/.config/opencode/opencode.json (guide):

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lovrabet-dataset": {
      "type": "local",
      "command": ["npx", "-y", "@lovrabet/dataset-mcp-server"],
      "env": {
        "LOVRABET_APP_CODE": "your-app-code"
      }
    }
  }
}

Qoder​

In Qoder Settings, go to MCP Server > + Add > Use the standard config.

Or use the Qoder CLI (guide):

Project wide:

qodercli mcp add lovrabet-dataset -- npx -y @lovrabet-dataset-mcp-server

Globally:

qodercli mcp add -s user lovrabet-dataset -- npx -y @lovrabet-dataset-mcp-server

Trae​

Go to Settings -> MCP Servers -> + Add. Use the standard config above.

Windsurf​

Follow the MCP configure guide using the standard config.

Global Installation​

If you don't want to use npx every time, you can install globally:

npm install -g @lovrabet/dataset-mcp-server

Then configure using the local command:

{
  "mcpServers": {
    "lovrabet-dataset": {
      "command": "lovrabet-dataset-mcp",
      "env": {
        "LOVRABET_APP_CODE": "your-app-code"
      }
    }
  }
}

Verify Configuration​

After configuration, enter in your AI editor:

List all datasets

If the dataset list is returned, the configuration is successful.

Troubleshooting​

MCP Server Won't Start​

  1. Check Node.js version: Requires Node.js >= 18

    node --version

  2. Test MCP server:

    npx -y @lovrabet/dataset-mcp-server

  3. Check logs: Set MCP_DEBUG=1 environment variable for verbose logging

If authentication error occurs, enter in your AI editor:

Please help me login to Lovrabet

Config File Locations​

EditorConfig File Path
Claude Desktop (Mac)~/Library/Application Support/Claude/claude_desktop_config.json
Claude Desktop (Win)%APPDATA%\Claude\claude_desktop_config.json
Claude Code~/.claude/settings.json
Cursor.cursor/mcp.json
Codex~/.codex/config.toml
OpenCode~/.config/opencode/opencode.json
Windsurf.windsurf/mcp_config.json

References​