How to Use the Arize AI MCP in Claude Code

Connect Claude Code to the Arize AI MCP Server. Run headless evaluations and fetch ML metrics straight from your terminal.

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

Trigger CI/CD Evals with the Arize AI MCP Server

Your deployment pipeline needs automated Arize AI checks before merging. You can drop this tool into a GitHub Action and let your agent verify model performance. It fires off `run_eval` to check for toxicity or hallucinations on the new build. The terminal agent handles the entire verification sequence. It checks the historical automated runs using `list_evals` and compares the new scores. If the new prompt fails the baseline, the script exits with an error and blocks the merge.

Pull Telemetry and Metrics in the Shell

SREs do not want to click through web interfaces during an incident, so this server brings the data to the shell. You can pipe your observability stats straight into your SSH session. The agent fetches the production data using `get_metrics` and dumps it to stdout. Finding the right targets takes seconds. The CLI hits `list_environments` and `list_models` to locate the exact deployment causing issues. It grabs the schema with `get_model` so you know exactly which features are drifting.

Manage Datasets and Ingest Logs

Syncing local test runs to your monitoring platform is usually a pain without this integration. Now you just pipe your local JSON output into the agent and tell it to push the traces via `ingest_log`. The payload hits the API instantly. Organizing those traces is just as easy from the command line. Your agent pulls your workspace boundaries using `list_spaces` and fetches static baselines with `list_datasets`. You get full platform control without ever leaving your tmux session.

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-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-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-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 the mcp add command with the HTTP transport flag and your Vinkius URL. Make sure you put all flags before the server name. Check your ~/.claude.json file to verify the settings saved correctly.

Yes. You can run the CLI in a headless container. It will execute the evaluation run, check the results, and fail the CI pipeline if the metrics drop below your threshold.

Ask the agent to fetch the specific model stats and output them as raw JSON. You can then pipe that stdout directly into jq or another processing script.

The API will reject it. The agent will show you the exact validation error in the terminal so you can fix your JSON structure and try again.

Vinkius handles authentication at the edge. When your shell script pushes raw telemetry logs or fetches PII filtering results, the request routes through a secure, ephemeral sandbox. No data persists after the command finishes.

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