Skip to content
AI & MLClaude Desktop Guide

Azure Machine Learning Datastore Management Client Claude Desktop Integration

This guide explains how to configure Claude Desktop (Mac and Windows) to use the Azure Machine Learning Datastore Management Client API through the Model Context Protocol (MCP). The integration exposes 8 API endpointsas callable tools inside Claude's chat interface, including Get Datastores list., Create or update a Datastore., Delete all Datastores., and more. No API keys or credentials are needed — setup takes approximately 30 seconds. The server runs locally via npx and communicates over STDIO transport. Paste the JSON configuration below into your claude_desktop_config.json file to get started.

Integration Specs

ClientClaude Desktop
Runtimenpx
AuthenticationNone
Setup Time~30 sec

Setup Instructions

1

Open Claude Settings

Launch Claude Desktop, open Settings (click your profile) → Developer → click 'Edit Config'.

2

Locate configuration file

This opens your local 'claude_desktop_config.json' file in your system editor.

3

Insert Server Config JSON

Paste the JSON configuration schema block (provided below) into the 'mcpServers' object.

4

Add authentication credentials

No credentials needed; leave the 'env' mapping empty.

5

Restart Claude app

Save the config file and restart Claude Desktop to load your new tools.

Configuration JSON

claude_desktop_config.json

Copy and paste this config snippet inside your local configuration file.

{
  "mcpServers": {
    "azure-com-machinelearningservices-datastore": {
      "command": "npx",
      "args": [
        "-y",
        "@mcp/azure-com-machinelearningservices-datastore"
      ],
      "env": {
        "AZURE_MACHINE_LEARNING_DATASTORE_MANAGEMENT_CLIENT_API_KEY": "your_azure_machine_learning_datastore_management_client_api_key"
      }
    }
  }
}

Required Environment Keys

Provide these variable keys in your local environment section:

AZURE_MACHINE_LEARNING_DATASTORE_MANAGEMENT_CLIENT_API_KEY

Replace your_azure_machine_learning_datastore_management_client_api_key with your secret key credentials.

Available Tools (8)

These endpoints are parsed from the OpenAPI schema and converted to Claude-compatible tools:

GET/datastore/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/datastores
Get Datastores list.
POST/datastore/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/datastores
Create or update a Datastore.
DELETE/datastore/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/datastores
Delete all Datastores.
GET/datastore/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/datastores/{name}
Get Datastore details.
PUT/datastore/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/datastores/{name}
Update or create a Datastore.
DELETE/datastore/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/datastores/{name}
Delete a Datastore.
GET/datastore/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/default
Get the default Datastore.
PUT/datastore/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/default/{name}
Set a default Datastore.