How to Use the Arize AI MCP in Mastra AI

Q: Can Mastra AI trigger Arize AI evaluation runs?

Yes, you include the runeval tool in your agent workflow. You can chain this after a generation step to keep your model quality high automatically.

Build complex observability workflows in Mastra AI with this managed MCP Server.

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 Mastra AI

Create your Vinkius account to connect Arize AI to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated model monitoring in Mastra AI

Use `list_models` and `get_metrics` to build agents that watch for performance degradation. You can set up conditional branches in your Mastra AI workflow to alert engineers if metrics dip below your thresholds. It handles the heavy lifting of data retrieval. Your agents simply process the output from `get_model` to decide if a model needs retraining or further investigation.

Triggering evaluations via Mastra AI

Execute `run_eval` as part of your automated agent tasks. This lets your system verify LLM outputs for toxicity or hallucinations immediately after a process completes. Use `list_evals` to confirm which tests are available before firing them. It allows your Mastra AI agents to select the right evaluation strategy based on the specific model context.

Managing workspaces with Mastra AI

Organize your telemetry pipeline by calling `list_spaces` and `list_environments`. You can programmatically route logs to the correct Arize AI destination based on your workflow state. Keep your data clean by checking environment configurations first. Your agents ensure that production logs don't mix with training data through these explicit tool calls.

Setup guide

Set up Arize AI MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Arize AI tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "arize-ai-mcp-client",
  servers: {
    "arize-ai-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Arize AI Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Arize AI tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Arize AI transactions"
);
console.log(result.text);

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 Mastra AI

You initialize the MCP client in your Mastra agent definition and spread the tools into the agent's tool set. This gives your agent immediate access to the entire Arize AI feature set.

Yes, you include the `run_eval` tool in your agent workflow. You can chain this after a generation step to keep your model quality high automatically.

You can use the built-in workflow engine in Mastra AI to implement retries or fallbacks. If an Arize AI tool call fails, your agent catches the error and decides the next move.

Vinkius handles the auth handshake, so you only provide your endpoint token to the client. This keeps your credentials out of your agent code.

We use an ephemeral V8 sandbox to isolate your MCP traffic. Your raw inference logs and model metadata are encrypted and never exposed beyond your designated Mastra AI agent workspace.

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