MCP Now
Verodat

Verodat

by Verodat
GitHub

Interact with Verodat AI Ready Data platform

verodat
account
dataset
workspace
server

Verodat MCP Server

MCP smithery badge

Overview

A Model Context Protocol (MCP) server implementation for Verodat, enabling seamless integration of Verodat's data management capabilities with AI systems like Claude Desktop.

image

Features

  • Account & Workspace Management
    • List accessible accounts
    • Browse workspaces within accounts
  • Dataset Operations
    • Create datasets with custom schemas and validation
    • Query and filter datasets
    • Retrieve dataset records
  • AI Integration
    • Fetch workspace context for AI processing
    • Execute AI-powered queries on datasets

Prerequisites

  • Node.js (v18 or higher)
  • Git
  • Claude Desktop (for Claude integration)
  • Verodat account and AI API key

Quick Start

Installing via Smithery

To install Verodat MCP Server for Claude Desktop automatically via Smithery:

1npx -y @smithery/cli install @Verodat/verodat-mcp-server --client claude

Manual Installation

  1. Clone the repository:

    1git clone https://github.com/Verodat/verodat-mcp-server.git
2cd verodat-mcp-server

  2. Install dependencies and build:

    1npm install
2npm run build

  3. Configure Claude Desktop:

    Create or modify the config file:

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

    Add the following configuration:

    1{
2    "mcpServers": {
3        "verodat": {
4            "command": "node",
5            "args": ["path/to/verodat-mcp-server/build/src/index.js"],
6            "env": {
7                "VERODAT_AI_API_KEY": "your-verodat-ai-api-key"
8            }
9        }
10    }
11}

Getting Started with Verodat

  1. Sign up for a Verodat account at verodat.com
  2. Generate an AI API key from your Verodat dashboard
  3. Add the API key to your Claude Desktop configuration

Available Commands

The server provides the following MCP commands:

1// Account & Workspace Management
2get-accounts        // List accessible accounts
3get-workspaces     // List workspaces in an account
4get-queries 		// Retrieve existing AI queries
5
6// Dataset Operations
7create-dataset     // Create a new dataset
8get-datasets      // List datasets in a workspace
9get-dataset-output // Retrieve dataset records
10get-dataset-targetfields // Retrieve dataset targetfields
11upload-dataset-rows  // Add new data rows to an existing dataset
12
13// AI Operations
14get-ai-context     // Get workspace AI context
15execute-ai-query   // Run AI queries on datasets

Debugging

The MCP server communicates over stdio, which can make debugging challenging. We provide an MCP Inspector tool to help:

1npm run inspector

This will provide a URL to access debugging tools in your browser.

Contributing

We welcome contributions! Please feel free to submit a Pull Request.

License

LICENSE file for details

Support