Verodat

Provides Verodat MCP access to accounts, workspaces, datasets, and AI-context queries from Claude Desktop.

javascript

0

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

Verodat MCP Server lets you plug Verodat’s data sources and AI-enabled queries into your Model Context Protocol workflow. It enables you to manage accounts, workspaces, datasets, and AI contexts from an MCP client, making it practical to integrate Verodat’s capabilities with Claude Desktop and similar AI environments.

How to use

You use Verodat MCP Server from your MCP client by configuring a local or remote MCP connection. Start the server as a stdio process and point your client to the built-in Verodat MCP runtime. Provide your Verodat AI API key to enable secure access to datasets, workspaces, and AI-context queries. You can run the server locally and connect via Claude Desktop or any MCP client that supports stdio MCP connections.

How to install

Prerequisites you need before starting are Node.js, Git, and access to Claude Desktop. Install each in order, then download and build the Verodat MCP Server.

# 1) Install Node.js
# Mac (Homebrew)
brew install node

# Mac (Manual)
# - Download macOS Installer from the Node.js site
# - Run the installer and restart the terminal

# Verification (Mac)
node -v
npm -v

# Windows (Installer)
# - Download Windows Installer
# - Run the installer and restart

# Verification (Windows)
node -v
npm -v

# 2) Install Git
# Mac (Homebrew)
brew install git

# Windows (Installer)
# - Download Git for Windows and install

# Verification (Mac)
git --version

# Verification (Windows)
git --version

# 3) Install Claude Desktop
# Mac: download Claude Desktop .dmg and install, then sign in
# Windows: download Claude Desktop .exe and install

Download Verodat MCP Server locally and install dependencies

git clone https://github.com/ThinkEvolveSolve/verodat-mcp-server.git
cd path/to/verodat-mcp-server
npm install
npm run build

Configure Verodat MCP-Server in Claude Desktop

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

Additional notes

Debugging tip: since MCP servers communicate over stdio, debugging can be challenging. Use the MCP Inspector to access debugging tools in your browser. Run the inspector tool with:

npm run inspector

Available tools

get-accounts

Lists available accounts you can access.

get-workspaces

Lists all workspaces within a specified account.

create-dataset

Creates a new dataset with defined schema and validation rules.

get-datasets

Retrieves datasets from a workspace with filtering capabilities.

get-dataset-output

Retrieves actual data records from a dataset.

get-ai-context

Retrieves workspace context including dataset configurations.

execute-ai-query

Executes AI-powered queries on dataset data.