How to Use the Arize AI MCP in Claude

Q: How do I connect Arize AI to my Claude Desktop app?

You add the server configuration to your claudedesktopconfig.json file under the mcpServers key. Once saved, restart your Claude Desktop app, and you will see the tools active via the hammer icon in your chat window.

Q: Can Claude Desktop automatically create new evaluation datasets in Arize AI?

Yes, the agent uses the createdataset tool to generate datasets directly from your conversation history or log files. You just ask Claude Desktop to save the specific data, and it executes the API call immediately.

Q: How does Claude Desktop help me analyze spans from Arize AI?

The client runs the listspans tool to pull trace data into your active prompt context. Your agent then parses these spans to identify latency bottlenecks or bad outputs in your LLM chain.

Q: Can I view my active ML projects using this tool?

Yes, you can list your projects using the listprojects tool. This lets you select the exact environment you need to inspect before pulling specific model details.

Pull model spans and datasets directly into Claude Desktop to troubleshoot prediction drift without leaving your chat.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arize AI MCP to Claude Desktop

Create your Vinkius account to connect Arize AI to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Arize AI with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inspect live model spans in Claude Desktop

The `list_spans` tool pulls raw execution traces from your Arize projects directly into your Claude Desktop chat window. You get immediate access to exact latency metrics, input-output pairs, and execution steps without switching tabs to a heavy browser UI. Your agent reads these traces to pinpoint where a pipeline failed or why a specific LLM call returned garbage. It maps out the exact sequence of events so you can fix the underlying prompt or model configuration instantly.

Track and create evaluation datasets

This MCP Server uses `list_datasets` and `create_dataset` to manage your benchmark data right inside the chat interface. You can scan existing evaluation sets or spin up new ones when your agent identifies problematic production outputs that need regression testing. Instead of exporting CSV files manually, you tell your agent to capture a bad run and format it. The server saves the payload directly to Arize, building your test suite while you discuss the fix.

Audit model experiments side-by-side

The `list_experiments` tool retrieves your historical evaluation runs while `get_model` and `list_projects` fetch the exact architecture details of your deployed systems. This lets your agent compare different prompt versions or model weights side-by-side. You spot regression trends immediately by letting Claude Desktop parse the performance metrics of each run. It highlights which version decreased latency or improved accuracy, giving you clear data to back up your deployment decisions.

Setup guide

Set up Arize AI MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Arize AI MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Arize AI MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under arize-ai-alternative-mcp.

json

{
  "mcpServers": {
    "arize-ai-alternative-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Arize AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Arize AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Arize AI MCP in Claude Desktop

You add the server configuration to your `claude_desktop_config.json` file under the `mcpServers` key. Once saved, restart your Claude Desktop app, and you will see the tools active via the hammer icon in your chat window.

Yes, the agent uses the `create_dataset` tool to generate datasets directly from your conversation history or log files. You just ask Claude Desktop to save the specific data, and it executes the API call immediately.

The client runs the `list_spans` tool to pull trace data into your active prompt context. Your agent then parses these spans to identify latency bottlenecks or bad outputs in your LLM chain.

Yes, you can list your projects using the `list_projects` tool. This lets you select the exact environment you need to inspect before pulling specific model details.

Yes, because all requests run through a secure V8 isolate sandbox that handles authentication locally. Your raw spans, datasets, and experiment logs are never stored on external servers, keeping your production data strictly between your local client and your Arize account.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript