Back to MCP Catalog

Verodat Data Management MCP Server

Data Science ToolsJavaScript
Access and manage Verodat's data capabilities through AI models
Available Tools

get-accounts

Retrieve available Verodat accounts

get-workspaces

List workspaces within a Verodat account

get-datasets

List datasets in a workspace

get-dataset-output

Retrieve actual data from a dataset

get-dataset-targetfields

Retrieve field definitions for a dataset

get-queries

Retrieve existing AI queries

get-ai-context

Get workspace context and data structure

execute-ai-query

Execute AI-powered queries on datasets

create-dataset

Create a new dataset with defined schema

upload-dataset-rows

Upload data rows to existing datasets

Verodat MCP Server provides a standardized interface for AI models to interact with Verodat's data management platform. It enables seamless integration between AI systems like Claude Desktop and Verodat's powerful data consumption, design, and management capabilities. Through this integration, users can retrieve, analyze, create, and manipulate datasets directly through conversational AI interfaces.

Introduction

Verodat MCP Server enables AI models to interact with Verodat's data management platform through a standardized interface. This integration allows you to leverage AI models like Claude to work with your data in Verodat, performing operations from simple data retrieval to complex dataset creation and management.

Prerequisites

Before installing the Verodat MCP Server, ensure you have:

  • Node.js v18 or higher
  • A Verodat account (sign up at verodat.com)
  • A Verodat AI API key (generated from your Verodat dashboard)
  • Claude Desktop (for Claude integration)

Installation Options

Option 1: Install via Smithery (Recommended)

The easiest way to install Verodat MCP Server for Claude Desktop is through Smithery:

npx -y @smithery/cli install @Verodat/verodat-mcp-server --client claude

Option 2: Manual Installation

  1. Clone the repository:
git clone https://github.com/Verodat/verodat-mcp-server.git
cd verodat-mcp-server
  1. Install dependencies and build:
npm install
npm run build
  1. Configure Claude Desktop by modifying the config file:
    • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%/Claude/claude_desktop_config.json

Configuration

The Verodat MCP Server offers three different capability levels that you can configure:

  1. Consume (8 tools for data retrieval)
  2. Design (9 tools, includes dataset creation)
  3. Manage (10 tools, includes data upload)

You can configure one or more of these capability levels in your Claude Desktop configuration file. Here's an example configuration for the "Consume" level:

{
  "mcpServers": {
    "verodat-consume": {
      "command": "node",
      "args": [
        "path/to/verodat-mcp-server/build/src/consume.js"
      ],
      "env": {
        "VERODAT_AI_API_KEY": "your-api-key",
        "VERODAT_API_BASE_URL": "https://verodat.io/api/v3"
      }
    }
  }
}

Replace "your-api-key" with your actual Verodat AI API key, and adjust the path to the built JavaScript file as needed.

Environment Variables

The following environment variables are required:

  • VERODAT_AI_API_KEY: Your Verodat API key for authentication
  • VERODAT_API_BASE_URL: The base URL for the Verodat API (defaults to "https://verodat.io/api/v3")

Getting Started

After installation and configuration, restart Claude Desktop. You can now interact with your Verodat data by asking Claude to:

  1. List your available accounts
  2. Show workspaces within an account
  3. Retrieve datasets from a workspace
  4. Execute queries on your data
  5. Create new datasets (if using Design or Manage capability)
  6. Upload data (if using Manage capability)

Example prompts:

  • "Show me all my Verodat accounts"
  • "List the datasets in my Marketing workspace"
  • "Create a visualization of my sales data from Q2"
  • "Create a new dataset for customer feedback"

Troubleshooting

If you encounter issues:

  1. Verify your API key is correct
  2. Check that the paths in your configuration file are correct
  3. Ensure Node.js is properly installed
  4. Restart Claude Desktop after making configuration changes
  5. Check the Claude Desktop logs for any error messages

Related MCPs

Vega-Lite Data Visualization
Data Science ToolsPython

Create interactive data visualizations using Vega-Lite syntax

Open Data
Data Science ToolsPython

Connect any Open Data to any LLM with Model Context Protocol

Tinybird
Data Science ToolsPython

Query and interact with Tinybird workspaces from any MCP client

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.