Skip to content
Developer ToolsClaude Desktop Guide

Artifact Claude Desktop Integration

This guide explains how to configure Claude Desktop (Mac and Windows) to use the Artifact API through the Model Context Protocol (MCP). The integration exposes 10 API endpointsas callable tools inside Claude's chat interface, including Get Batch Artifacts by Ids., Create Artifact., Create an Artifact for an existing data location., 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-artifact": {
      "command": "npx",
      "args": [
        "-y",
        "@mcp/azure-com-machinelearningservices-artifact"
      ],
      "env": {
        "ARTIFACT_API_KEY": "your_artifact_api_key"
      }
    }
  }
}

Required Environment Keys

Provide these variable keys in your local environment section:

ARTIFACT_API_KEY

Replace your_artifact_api_key with your secret key credentials.

Available Tools (10)

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

POST/artifact/v2.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/artifacts/batch/metadata
Get Batch Artifacts by Ids.
POST/artifact/v2.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/artifacts/metadata
Create Artifact.
POST/artifact/v2.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/artifacts/register
Create an Artifact for an existing data location.
POST/artifact/v2.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/artifacts/storageuri/batch/metadata
Get Batch Artifacts storage by Ids.
GET/artifact/v2.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/artifacts/{origin}/{container}
Get Artifacts metadata in a container or path.
DELETE/artifact/v2.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/artifacts/{origin}/{container}/batch
Delete Artifact Metadata.
POST/artifact/v2.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/artifacts/{origin}/{container}/batch/ingest/containersas
Batch ingest using shared access signature.
POST/artifact/v2.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/artifacts/{origin}/{container}/batch/metadata
Create a batch of empty Artifacts.
POST/artifact/v2.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/artifacts/{origin}/{container}/batch/metadata:delete
Delete Batch of Artifact Metadata.
GET/artifact/v2.0/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/artifacts/{origin}/{container}/content
Get Artifact content by Id.