Verodat MCP Server

🚀 Verodat MCP Layer Architecture Diagram

🚀 Quick Start

This document guides you on how to use Verodat (https://verodat.io) in the Model Context Protocol server, which is used to insert code and data into AI systems like Claude Desktop.

✨ Features

The current Verodat MCP server offers the following tools:

• Account and Workspace Management:
  • get-accounts - List all accounts you have access to.
  • get-workspaces - List all workspaces in a specified account.
• Dataset Operations:
  • create-dataset - Create a new dataset with a defined schema and validation rules.
  • get-datasets - Retrieve datasets from a workspace with filtering capabilities.
  • get-dataset-output - Retrieve the actual data records in a dataset.
• AI and Context:
  • get-ai-context - Retrieve the workspace context, including dataset configurations.
  • execute-ai-query - Execute AI-driven queries on dataset data.

📦 Installation

Installation Requirements

1. Node.js: Make sure Node.js is installed. You can download and install it from https://nodejs.org.
2. Git: Ensure Git is installed. You can download and install it from https://git-scm.com/downloads.
3. Claude Desktop:

• Mac: Visit https://claude.ai/download to download the macOS version.
• Windows: Visit https://claude.ai/download to download the Windows version.

Installation Steps

1. Open a terminal or command prompt and run the following command to clone the Verodat MCP server repository:

   git clone https://github.com/ThinkEvolveSolve/verodat-mcp-server.git
   

2. Navigate to the path/to/verodat-mcp-server directory and run the following commands to install dependencies and build the project:

   npm install
   npm run build
   

💻 Usage Examples

Configure the Verodat MCP Server in Claude Desktop

To use it with Claude Desktop, follow these configuration steps:

MacOS

Edit the ~/Library/Application Support/Claude/claude_desktop_config.json file and add the following content:

{
    "mcpServers": {
        "verodat": {
            "command": "node",
            "args": [
                "path/to/verodat-mcp-server/build/src/index.js"
            ],
            "env": {
                "VERODAT_AI_API_KEY": "<<your-verodat-ai-api-key>>"
            }
        }
    }
}

Windows

Edit the %APPDATA%/Claude/claude_desktop_config.json file and add the following content:

{
    "mcpServers": {
        "verodat": {
            "command": "node",
            "args": [
                "path/to/verodat-mcp-server/build/src/index.js"
            ],
            "env": {
                "VERODAT_AI_API_KEY": "<<your-verodat-ai-api-key>>"
            }
        }
    }
}

Register for Verodat

You can register for a Verodat account here: https://verodat.com.

Get an AI API Key

Log in to your Verodat account, generate your AI API key, and replace it in the following configuration file:

"VERODAT_AI_API_KEY": "<<your-verodat-ai-api-key>>"

Debugging

Since the MCP server communicates via stdio, debugging can be challenging. We recommend using the MCP inspector, which is available as a package script:

npm run inspector

The inspector will provide a URL in the browser to access the debugging tools.