How to Use the Arize AI MCP in Windsurf

Q: How does Windsurf connect to my Arize AI projects?

You add the server configuration to your Windsurf mcpconfig.json file. Windsurf then detects the endpoint and allows Cascade to call tools like listprojects on your Arize AI dashboard.

Q: Do I need to manually import datasets from Arize AI into Windsurf?

No, you don't. Cascade uses listdatasets to read your Arize AI test datasets directly from your Windsurf workspace, so there is zero file swapping.

Q: Can Cascade create new Arize AI test runs in Windsurf?

Yes, Cascade uses the createdataset tool to push local test cases from Windsurf back up to your Arize AI monitoring suite. This lets you track how your local code edits affect production performance.

Let Windsurf autonomously pull Arize AI spans, detect drift, and build evaluation runs without manual prompting.

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 Windsurf

Create your Vinkius account to connect Arize AI to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug latency drift with Windsurf and Arize AI

Cascade can trace slow LLM steps directly in your Windsurf workspace. By calling `list_spans`, the agent pulls raw telemetry from your Arize AI projects to pinpoint lagging chains. Once Cascade finds the bottleneck, it writes a fix and tests it inside Windsurf. You don't have to copy-paste Arize AI trace IDs because this MCP Server keeps the context live in your editor.

Run Arize AI evaluations automatically using Windsurf

When you change a prompt in Windsurf, Cascade uses `list_experiments` to check how your older Arize AI models behaved. The agent grabs historical performance metrics and compares them to your current local branch. If the performance drops, Cascade uses `create_dataset` to spin up a new Arize AI test suite based on real-world production failures. It does this in one Windsurf step, saving you from bouncing between your editor and your monitoring dashboard.

Audit Arize AI production models inside Windsurf

Spotting Arize AI data drift shouldn't require opening fifty browser tabs when you are coding in Windsurf. This MCP Server lets your editor fetch model details using `get_model` and check active monitoring projects via `list_projects`. Cascade reads these Arize AI metrics, spots feature drift, and alerts you before users start complaining about bad predictions. It's a direct bridge between your production observability stack and your Windsurf workspace.

Setup guide

Set up Arize AI MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Arize AI payment history." If connected, Cascade will call the Arize AI tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

You add the server configuration to your Windsurf `mcp_config.json` file. Windsurf then detects the endpoint and allows Cascade to call tools like `list_projects` on your Arize AI dashboard.

Yes, Cascade can run a multi-step workflow inside Windsurf. It pulls the bad inputs using `list_spans`, writes a regression test in your local code, and updates your Arize AI model parameters to fix the issue.

No, you don't. Cascade uses `list_datasets` to read your Arize AI test datasets directly from your Windsurf workspace, so there is zero file swapping.

Yes, Cascade uses the `create_dataset` tool to push local test cases from Windsurf back up to your Arize AI monitoring suite. This lets you track how your local code edits affect production performance.

Your Arize AI tracing spans and project metrics stay inside a secure Vinkius V8 sandbox connected to Windsurf. The server only passes raw JSON payloads directly to your local editor, keeping your telemetry data isolated from external eyes.

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