How to Use the Arize AI MCP in Cursor

Q: Does this work with any model in Arize?

Yes, it works with any model you're tracking in Arize. The listmodels and listenvironments tools let you see everything you have access to, so you can easily find the right IDs and names to use in your prompts.

Inject live Arize AI model data directly into your code with Cursor's agent mode.

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 Cursor

Create your Vinkius account to connect Arize AI to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Code with Live Model Metrics

Stop mocking API responses for your MLOps tools. Ask Cursor's agent to `get_metrics` for a production model, and it will inject the actual JSON response into your editor. You can write parsers and build dashboards with real data from the start. Need to know what's available? Have the agent call `list_models` or `list_spaces` and drop the output right into a comment block. It's a fast way to discover model IDs and environment names without switching windows.

Automate Evaluation Scripts

Build your evaluation scripts faster. Tell Cursor to trigger an LLM quality check using `run_eval`. The agent can then use `list_evals` to poll for the result, giving you a complete, working script for your CI/CD pipeline. This isn't just for one-off checks. You can build entire workflows inside the editor. For instance, ask the agent to `get_dataset`, process it, and then use `ingest_log` to send the transformed data back to Arize, all from a single prompt.

Your Arize AI MCP Server in Cursor

This MCP Server turns Cursor into a true MLOps command center. You're not just writing code; you're interacting with your live model infrastructure. Get model definitions with `get_model` to understand inputs and outputs before you write a single line of integration code. The connection is project-specific. Just drop the `mcp.json` file in your project's `.cursor` directory. Now anyone who clones the repo gets the same powerful access to Arize, right inside their editor.

Setup guide

Set up Arize AI MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Arize AI MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Arize AI transactions." If the MCP tools are loaded correctly, Cursor will call the Arize AI tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

You enable Cursor's agent mode and it uses the Arize AI server to call tools. When you ask it to 'get metrics for model X', the agent calls the `get_metrics` tool and inserts the live data directly into your code file. It's like having a junior dev who can pull live API data for you.

Absolutely. You can use Cursor to prototype the scripts. Ask the agent to call `run_eval`, then `list_evals` to check the results. Once the logic works in the editor, you can copy that script into your actual CI/CD system.

The agent injects live data directly into your code. Instead of getting a text description of your model metrics, Cursor's agent will call `get_metrics` and write the actual JSON response into the file you're editing. This saves a ton of time.

Yes, it works with any model you're tracking in Arize. The `list_models` and `list_environments` tools let you see everything you have access to, so you can easily find the right IDs and names to use in your prompts.

Your Arize model metadata and telemetry logs are only accessed when you explicitly command the agent. The connection uses your Vinkius token for authentication, and the server runs in a zero-trust, ephemeral environment. No data is persisted on the MCP server.

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