How to Use the Arize AI MCP in VS Code Copilot

Q: How do we share the Arize AI configuration across our team in VS Code Copilot?

You commit the MCP settings to a .vscode/mcp.json file in your repository root. Every developer using VS Code Copilot will automatically have access to the tools when they open the workspace.

Q: Can VS Code Copilot pull metrics from my Arize AI experiments?

Yes, Copilot uses the listexperiments tool to fetch your evaluation history directly into the chat. You can ask it to compare performance metrics across different runs to verify your local changes.

Q: How does VS Code Copilot use Arize AI spans to find errors?

The client runs the listspans tool to pull recent execution traces into your current context. Copilot then analyzes the trace payload to pinpoint exactly where an LLM execution failed or timed out.

Q: How do I fetch details for a specific model?

You run the getmodel tool by asking Copilot to retrieve details for a specific model ID. The client returns the architecture and performance parameters directly in your chat sidebar.

Equip your engineering team with real-time Arize AI model traces and datasets inside VS Code Copilot for faster production debugging.

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

Inspect live spans with VS Code Copilot

The `list_spans` tool allows your team to query live production traces directly within their shared workspace. This means developers can collaborate on debugging live model regressions without sharing screenshots of external dashboards. VS Code Copilot reads the trace data to identify where a model pipeline is failing. Because the configuration is committed to your repository, every engineer on the team can run these diagnostics instantly.

Manage evaluation datasets from the workspace

This MCP Server uses `list_datasets` and `create_dataset` to keep your evaluation suites synchronized with your codebase. Developers can inspect existing test sets or upload new ones as they update their LLM prompts. Copilot helps you write scripts that fetch these datasets, run local evaluations, and push the results back. This keeps your model development cycle tightly integrated with your standard git workflow.

Audit model experiments during code review

The `list_experiments` tool pulls evaluation metrics while `get_model` and `list_projects` fetch active model configurations into your workspace. This allows your team to audit model performance metrics during pull request reviews. Instead of relying on subjective feedback, Copilot analyzes the experiment logs to verify if a prompt change actually improved output quality. You get objective, data-driven decisions before merging code to main.

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-alternative-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

You commit the MCP settings to a `.vscode/mcp.json` file in your repository root. Every developer using VS Code Copilot will automatically have access to the tools when they open the workspace.

Yes, Copilot uses the `list_experiments` tool to fetch your evaluation history directly into the chat. You can ask it to compare performance metrics across different runs to verify your local changes.

The client runs the `list_spans` tool to pull recent execution traces into your current context. Copilot then analyzes the trace payload to pinpoint exactly where an LLM execution failed or timed out.

You run the `get_model` tool by asking Copilot to retrieve details for a specific model ID. The client returns the architecture and performance parameters directly in your chat sidebar.

Yes, all data transmission occurs over secure, encrypted channels managed by Vinkius. Your projects, experiments, datasets, and spans are accessed on-demand with ephemeral sessions, meaning no telemetry or proprietary data is ever stored outside your environment.

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