How to Use the Arize AI MCP in Claude Code

Q: How do I add the Arize AI MCP Server to Claude Code?

Run claude mcp add --transport http arize-ai-alternative-mcp -- in your terminal. This registers the server and lets you query your Arize AI monitoring tools immediately.

Q: How does Claude Code display Arize AI evaluation experiments?

Claude Code uses listexperiments to fetch your runs and formats the results as a clean text table in your terminal. You can quickly see which Arize AI model variants performed best.

Pipe Arize AI drift metrics and evaluation spans directly into your terminal workflows using Claude Code.

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 Code

Create your Vinkius account to connect Arize AI to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Arize AI model health via Claude Code

Claude Code lets you audit your ML pipelines without leaving your terminal. By calling `list_projects` and `get_model`, the CLI tool pulls active drift alerts and Arize AI model health metrics directly into your shell. You can easily pipe these metrics to other CLI tools or grep for specific Arize AI model versions. This MCP Server eliminates the need to open a web browser just to check if your production model is failing.

Run headless Arize AI evaluations with Claude Code

Trigger evaluations during your deployment scripts. Claude Code uses `create_dataset` to upload your test prompts and `list_experiments` to verify the Arize AI evaluation results before shipping. If the Arize AI evaluation run fails, the CLI tool catches it and halts your deployment. This lets you build a continuous evaluation pipeline directly inside your Claude Code terminal environment.

Trace Arize AI LLM bottlenecks via Claude Code

Debugging slow agent steps is faster when you don't have to click through a UI. Claude Code uses `list_spans` to fetch Arize AI execution traces and latency metrics directly to stdout. You can ask Claude Code to analyze these spans, identify the slowest node in your chain, and print a summary. It makes troubleshooting production Arize AI latency as simple as running a shell command.

Setup guide

Set up Arize AI MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see arize-ai-alternative-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Arize AI transactions." It will automatically discover and invoke the available Arize AI tools.

Terminal

claude mcp add --transport http arize-ai-alternative-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Arize AI MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "arize-ai-alternative-mcp": {
      "type": "url",
      "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 Code

Run `claude mcp add --transport http arize-ai-alternative-mcp -- ` in your terminal. This registers the server and lets you query your Arize AI monitoring tools immediately.

Yes, you can tell Claude Code to parse local log files and run `create_dataset` to upload them. It handles the API formatting and uploads the data to Arize AI in one step.

Claude Code uses `list_experiments` to fetch your runs and formats the results as a clean text table in your terminal. You can quickly see which Arize AI model variants performed best.

Yes, Claude Code runs entirely in the terminal, so you can save its output or pipe trace spans from `list_spans` into local debugging utilities. This makes it easy to manipulate your Arize AI telemetry.

This MCP Server runs in a secure, isolated V8 sandbox that uses end-to-end token authentication. Your actual Arize AI dataset records and span traces never touch external storage, keeping your production data locked down inside Claude Code.

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