An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Arize AI to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage model health and performance through natural conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through Arize AI.

  1. 01

    Get model

    Use this capability to retrieve detailed metadata for a specific ML model.

  2. 02

    List experiments

    List all available ML experiments so you can track model performance and data quality.

  3. 03

    List projects

    List all active ML tracing projects to monitor different parts of your ML infrastructure.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Arize AI.

  1. 04

    List spans

    List recent execution spans, allowing you to analyze model traces and find performance bottlenecks.

  2. 05

    Create dataset

    Use this capability to programmatically create a new dataset for model evaluation and validation.

  3. 06

    List datasets

    List existing datasets to manage your model validation resources.

Real work

What teams actually run

01

Checking for Data Drift

Ask your agent to check model performance against the latest data to detect data drift immediately.

02

Validating New Models

Use the MCP to create a new dataset, then run validation checks on model versions against that dataset.

03

Debugging Latency Issues

Request a list of execution spans for a specific project to pinpoint where latency spikes are occurring.

04

Auditing Model Health

Retrieve detailed metadata for a model to verify its current status and operational settings.

Automate a task

Put Arize AI to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Arize AI works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Arize AI to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

841ms average. Fast in production.

Arize AI is checked daily against the live service.

Daily averagePeak 1007ms
Oct 3Today
Fastest day
748ms
Slowest day
1007ms
14-day trend
Slowing+13%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Arize AI, so you can see the experience inside your AI.

It does not authenticate your account with Arize AI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Arize AI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_wKJSgGsb2EgJmks5PzM3V0jknb7nFZgbwB0CaRFP/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Arize AI capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "arize-ai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_wKJSgGsb2EgJmks5PzM3V0jknb7nFZgbwB0CaRFP/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Arize AI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Arize AI owners hand off.

This MCP is built for technical teams who need to maintain and monitor complex machine learning systems. It lets you automate oversight tasks that usually require logging into multiple specialized dashboards.

  • 01

    ML Engineers

    Instantly retrieve span details and analyze model traces using natural language commands.

  • 02

    Data Scientists

    Monitor experiment results and manage datasets for validation without leaving your primary workspace.

  • 03

    AI Developers

    Automate the oversight of LLM and ML model health through simple, direct AI queries.

FAQ

Questions Arize AI owners ask.

  • 01

    What kind of data can I monitor with this MCP?

    You can monitor ML tracing projects, track model performance, and check for data drift. The MCP provides access to high-fidelity execution spans and telemetry data.

  • 02

    Do I need to manually log into Arize to use this?

    No. Your AI client handles the connection and data retrieval. You can orchestrate your entire ML observability pipeline directly through natural conversation.

  • 03

    How do I start tracking a new model?

    You can use the MCP to create a new dataset for model evaluation. Once the dataset is ready, you can begin uploading model versions for automated validation.

  • 04

    What if I need to check multiple models?

    You can retrieve detailed metadata for specific ML models, or you can list all available ML experiments to compare performance across different versions.

  • 05

    How do I find my Arize API Key?

    Log in to your account, navigate to Settings > API, and generate or copy your unique secret key.

  • 06

    Can I track model drift via AI?

    Yes! Use the list_experiments capability to retrieve data on active model evaluations and track performance variations programmatically.

  • 07

    How do I retrieve telemetry traces?

    Use the list_spans capability to retrieve high-fidelity execution spans and traces for your ML projects directly from the platform.

Explore

More in Friends

Suggestions

Connect Arize AI to Claude, Cursor, ChatGPT & more