Skip to content
MCP-Bridge
AI & MLClaude Desktop Guide

Azure Machine Learning Model Management Service Claude Desktop Integration

This guide explains how to configure Claude Desktop (Mac and Windows) to use the Azure Machine Learning Model Management Service API through the Model Context Protocol (MCP). The integration exposes 10 API endpointsas callable tools inside Claude's chat interface, including Query the list of Assets in a workspace., Create an Asset., Get an Asset., 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-modelmanagement": {
      "command": "npx",
      "args": [
        "-y",
        "@mcp/azure-com-machinelearningservices-modelmanagement"
      ],
      "env": {
        "AZURE_MACHINE_LEARNING_MODEL_MANAGEMENT_SERVICE_API_KEY": "your_azure_machine_learning_model_management_service_api_key"
      }
    }
  }
}

Required Environment Keys

Provide these variable keys in your local environment section:

AZURE_MACHINE_LEARNING_MODEL_MANAGEMENT_SERVICE_API_KEY

Replace your_azure_machine_learning_model_management_service_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/modelmanagement/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroup}/providers/Microsoft.MachineLearningServices/workspaces/{workspace}/assets
Query the list of Assets in a workspace.
POST/modelmanagement/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroup}/providers/Microsoft.MachineLearningServices/workspaces/{workspace}/assets
Create an Asset.
GET/modelmanagement/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroup}/providers/Microsoft.MachineLearningServices/workspaces/{workspace}/assets/{id}
Get an Asset.
DELETE/modelmanagement/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroup}/providers/Microsoft.MachineLearningServices/workspaces/{workspace}/assets/{id}
Delete an Asset.
PATCH/modelmanagement/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroup}/providers/Microsoft.MachineLearningServices/workspaces/{workspace}/assets/{id}
Update an Asset.
GET/modelmanagement/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroup}/providers/Microsoft.MachineLearningServices/workspaces/{workspace}/images/{imageId}/profiles
Get a list of Image Profiles.
POST/modelmanagement/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroup}/providers/Microsoft.MachineLearningServices/workspaces/{workspace}/images/{imageId}/profiles
Create a Profile.
GET/modelmanagement/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroup}/providers/Microsoft.MachineLearningServices/workspaces/{workspace}/images/{imageId}/profiles/{id}
Get a Profile.
GET/modelmanagement/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroup}/providers/Microsoft.MachineLearningServices/workspaces/{workspace}/models
Query the list of Models in a workspace.
POST/modelmanagement/v1.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroup}/providers/Microsoft.MachineLearningServices/workspaces/{workspace}/models
Register a model.
← View Config URLView Azure Machine Learning Model Management ServiceMCP Details →