How to Use the Arize AI MCP in VS Code Copilot

Q: How do I share the Arize AI configuration with my team in VS Code Copilot?

Create a .vscode/mcp.json file in your project's root directory. Add the Arize AI MCP Server configuration there and commit the file to your Git repository. Everyone who pulls the project will automatically have the tools available in Copilot Chat.

Q: Can we use Arize AI and VS Code Copilot to check for model drift?

Yes. You can ask Copilot's agent to use the getmetrics tool to fetch performance, drift, and data quality metrics for any model you're tracking in Arize. The results appear directly in the chat, so your team can quickly diagnose issues.

Q: Can I run my custom LLM evaluations?

You can. The runeval tool lets you kick off any evaluation you've configured in Arize. Just tell Copilot which evaluation to run on which model, and the server handles it.

Equip your whole team with Arize AI observability tools directly inside VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect Arize AI to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Team-Wide Model Observability

Put Arize access right where your team works. By adding the MCP Server config to `.vscode/mcp.json` and committing it, every developer on the project gets the same tools. No individual setup, no 'it works on my machine' problems. A new engineer can clone the repo and immediately ask Copilot to `list_models` or `get_model` details. It removes the friction of learning a new platform's UI and keeps them focused inside the editor.

Interact with Arize in Chat

Use Copilot Chat in Agent mode as your Arize command line. Ask it to `get_metrics` for a model that's showing drift. Copilot will return the data right in the chat panel, ready for you to analyze or copy. This is great for quick checks. You can `list_environments` to get the right name for production, or `list_evals` to see if the latest model passed its automated checks. It's faster than context-switching to a browser.

Your Arize MCP Server for VS Code

This server connects your engineering workflow to your MLOps platform. You can trigger new evaluation runs with `run_eval` or send new telemetry data using `ingest_log` without leaving VS Code. It bridges the gap between code and production monitoring. You can also manage your evaluation data right in the editor. Ask Copilot to `list_datasets` and then `get_dataset` to pull down a specific evaluation set. This is useful for debugging a model's performance on a known slice of data.

Setup guide

Set up Arize AI MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Arize AI MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Arize AI tools listed. Try asking: "List my recent Arize AI transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Create a `.vscode/mcp.json` file in your project's root directory. Add the Arize AI MCP Server configuration there and commit the file to your Git repository. Everyone who pulls the project will automatically have the tools available in Copilot Chat.

Yes. You can ask Copilot's agent to use the `get_metrics` tool to fetch performance, drift, and data quality metrics for any model you're tracking in Arize. The results appear directly in the chat, so your team can quickly diagnose issues.

It brings your MLOps tools into the editor your team already uses. The shared configuration ensures everyone has the same access, and interacting via chat is faster than navigating the Arize web UI for routine checks like listing models or fetching metrics.

You can. The `run_eval` tool lets you kick off any evaluation you've configured in Arize. Just tell Copilot which evaluation to run on which model, and the server handles it.

The server acts as a secure proxy, executing your commands. It only accesses your Arize model metadata and telemetry logs when requested. All requests are authenticated via your Vinkius token, and the server itself is stateless and operates within a sandboxed V8 isolate.

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