How to Use the Arize AI MCP in Windsurf

Q: How do I connect the Arize AI MCP Server to Windsurf?

Open your mcpconfig.json file in /.codeium/windsurf/ and add the endpoint. You can also use the Cascade settings UI to add it. Click refresh in the MCP panel and Cascade will auto-discover the observability tools.

Connect the Arize AI MCP Server to Windsurf. Let Cascade pull telemetry and trigger evaluations while you code.

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

Monitor ML Models with the Arize AI MCP Server

Arize AI observability doesn't require waiting for dashboard loads. When you push a new prompt version, Cascade grabs the environment data via `list_environments` and pulls the specific model features using `get_model`. You just tell it to analyze the latest deployment. The agent chains these checks automatically. It grabs the observability stats through `get_metrics` and compares them against your baseline. If something looks off, Cascade flags the exact drift vector in your editor before you even run a test suite.

Trigger Automated LLM Evaluations

Testing generative models takes time unless you run Arize AI checks locally. Now you just ask your IDE to run the toxicity or hallucination checks. Windsurf fires off `run_eval` directly against your workspace. Once the run finishes, Cascade pulls the results back into your context window. It checks `list_evals` to see historical performance, then writes the necessary prompt adjustments right into your source files.

Ingest Telemetry Logs on the Fly

Local testing usually means disconnected data, but this server fixes that. You can have your agent push raw traces straight to the platform using `ingest_log`. The payload hits your configured workspace instantly. Managing those workspaces is just as fast. Cascade maps out your available separation boundaries with `list_spaces` and grabs specific evaluation batches using `list_datasets`. Everything stays synced while you iterate on your application logic.

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-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

Open your mcp_config.json file in ~/.codeium/windsurf/ and add the endpoint. You can also use the Cascade settings UI to add it. Click refresh in the MCP panel and Cascade will auto-discover the observability tools.

Yes. Cascade can chain the commands without asking for permission. It will execute the evaluation, wait for the results, and show you the output in the chat panel.

Your API token might lack the right permissions. Make sure the token provided in your Windsurf configuration has read access for spaces and environments.

Ask Cascade to compare current performance against your baseline. It uses the metrics tool to fetch the data and does the math right in your IDE.

Vinkius runs the server in a V8 Isolate Sandbox. When your agent pushes raw telemetry logs or pulls PII filtering metrics, that data flows straight to the platform API. The server itself is ephemeral and retains zero state between requests.

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