Skip to content
AI & MLClaude Desktop Guide

Azure Machine Learning Workspaces Claude Desktop Integration

This guide explains how to configure Claude Desktop (Mac and Windows) to use the Azure Machine Learning Workspaces API through the Model Context Protocol (MCP). The integration exposes 10 API endpointsas callable tools inside Claude's chat interface, including Operations_List, Workspaces_ListBySubscription, Workspaces_ListByResourceGroup, 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-machinelearningservices": {
      "command": "npx",
      "args": [
        "-y",
        "@mcp/azure-com-machinelearningservices-machinelearningservices"
      ],
      "env": {
        "AZURE_MACHINE_LEARNING_WORKSPACES_API_KEY": "your_azure_machine_learning_workspaces_api_key"
      }
    }
  }
}

Required Environment Keys

Provide these variable keys in your local environment section:

AZURE_MACHINE_LEARNING_WORKSPACES_API_KEY

Replace your_azure_machine_learning_workspaces_api_key with your secret key credentials.

Available Tools (10)

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

GET/providers/Microsoft.MachineLearningServices/operations
Operations_List
GET/subscriptions/{subscriptionId}/providers/Microsoft.MachineLearningServices/workspaces
Workspaces_ListBySubscription
GET/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces
Workspaces_ListByResourceGroup
GET/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}
Workspaces_Get
PUT/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}
Workspaces_CreateOrUpdate
DELETE/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}
Workspaces_Delete
PATCH/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}
Workspaces_Update
GET/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/computes
MachineLearningCompute_ListByWorkspace
GET/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/computes/{computeName}
MachineLearningCompute_Get
POST/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/computes/{computeName}
MachineLearningCompute_SystemUpdate