How to Use the Arize AI MCP in Claude

Q: Can I trigger evaluations for Arize AI from Claude Desktop?

Yes. The runeval tool lets you start a new evaluation run directly from a chat prompt in Claude Desktop. You can also use listevals to check the status and results of previous runs.

Connect Claude Desktop to Arize AI and get real-time model observability right in 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

Check Model Performance Instantly

Ask Claude to pull live metrics for any model you're tracking. You can use `get_metrics` for specific versions or call `get_model` to see its full definition. It's much faster than digging through the Arize UI for a quick status check. Need to see what's available first? Just ask Claude to list what you need. Get a complete list of your tracked models with `list_models` or see all your configured `list_environments` like production or staging. Claude presents everything cleanly in the chat interface.

Run and Review Evaluations

You can trigger an LLM evaluation directly from your conversation. Use the `run_eval` tool to kick off a custom test for things like toxicity or PII leakage on a new model version. There's no need to open another tab or run a local script. Want to check on past results? The `list_evals` tool shows you all completed and ongoing evaluation runs. It's a quick way to verify if a new model passed its checks before you decide to deploy it.

Manage Datasets with Claude Desktop

Pull your static evaluation datasets directly into your Claude session. The `list_datasets` tool shows you what's available in Arize. Then, `get_dataset` fetches the specific one you need for analysis or review right on your screen. This MCP Server also lets you send new data to Arize. The `ingest_log` tool provides a direct line for feeding raw telemetry logs from your machine into the platform. It's a straightforward way to update your observability data.

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-mcp.

json

{
  "mcpServers": {
    "arize-ai-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

It connects Arize's tools directly to Claude's chat. You ask Claude to perform an action, like 'get metrics for model X,' and the server executes it against the Arize platform. This gives you instant access to your ML observability data without leaving the app.

You can monitor any ML model or LLM that you're tracking in your Arize account. The server lets you `list_models` to see all of them and `get_model` to pull specific details. It works across all your configured workspaces and environments.

Yes. The `run_eval` tool lets you start a new evaluation run directly from a chat prompt in Claude Desktop. You can also use `list_evals` to check the status and results of previous runs.

Not at all. If you use the Claude.ai website, you just paste the server URL into the Custom Connectors settings. For the desktop app, you add the server details to a single configuration file and restart.

The server only touches your Arize model metadata and telemetry logs when you tell it to. All communication is over HTTPS, and Vinkius isolates each server process in its own sandbox. Your credentials and raw data are not stored by the MCP server itself.

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