How to Use the Arize AI MCP in Cline

Bring ML observability straight into VS Code with this MCP Server. Cline uses Arize AI to pull metrics and write fixes for you.

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 Cline

Create your Vinkius account to connect Arize AI to Cline 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 Cline

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Cline Evaluates LLM Performance Automatically

Arize AI lets your agent fix hallucinating prompts autonomously. It starts by mapping out your available workspaces using `list_spaces` and checking the production setup via `list_environments`. No dashboard hunting required. Then it digs into the actual data. It pulls the specific evaluation dataset with `get_dataset` and triggers a custom run using `run_eval`. Once the results come back, the agent writes the prompt adjustments and stages the commit.

Fetch Observability Metrics via MCP

Checking data drift usually breaks your flow until you connect this server. Now you just ask your editor to pull the latest stats for your tracked models. The agent hits `list_models` to find the exact target and grabs the stats with `get_metrics`. It parses those inputs, outputs, and features directly. By running `get_model`, your AI client knows exactly what the schema looks like. It uses that context to write better test cases in your repository.

Push Raw Telemetry from Local Tests

Building custom LLM pipelines means generating a lot of local traces that need to reach Arize AI. Your agent can push those directly to the platform using `ingest_log`. You just run your local script and let the editor handle the upload. Keeping track of those automated runs is simple. The agent checks `list_evals` to pull toxicity or PII filtering results. If the new traces show regressions, it flags the exact line of code causing the issue.

Setup guide

Set up Arize AI MCP in Cline

Prerequisites

VS Code with Cline extension installed
Active Vinkius subscription with a valid endpoint token

1

Open Cline MCP settings

Click the Cline icon in the VS Code sidebar to open the Cline panel. Then click the MCP Servers icon (server stack) at the top-right corner of the panel.
2

Add a remote server

Click "Remote Servers" at the top, then click "Add Remote MCP". In the Name field, type arize-ai-mcp. In the URL field, paste your Vinkius endpoint: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp. Get your token from cloud.vinkius.com.
3

Enable the server

After saving, the server appears in the Cline MCP panel. Toggle the switch to enable it. The status indicator turns green when the connection is live.
4

Start using tools

Return to the Cline chat and ask: "Check my latest Arize AI refund status." Cline will discover the available tools and request your approval before invoking each one — giving you full control over every action.

Cline MCP Settings

{
  "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 Cline

Open the sidebar and click the MCP icon. You can use the Remote Servers tab to add the Vinkius endpoint URL. It connects via streamable HTTP transport immediately.

That is exactly what it does. If the hallucination scores are high, the agent will rewrite your prompt templates and show you the diff. It handles the entire feedback loop.

You just ask your agent to list them. It pulls the available datasets and can even read specific evaluation records to help you debug edge cases in your application.

The payload structure must match the required schema exactly. Ask your agent to verify the JSON format before it tries to push the logs.

The connection uses zero-trust architecture. Your AI client requests specific model features or pushes raw logs, and the Vinkius endpoint routes that directly to the provider. We never store your evaluation data on our infrastructure.

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