How to Use the Arize AI MCP in AutoGen

Q: How can my AutoGen agents use the Arize AI toolset?

After installing autogen-extmcp, you use the mcpservertools function with your Vinkius endpoint URL. This function fetches the Arize AI tools and prepares them to be passed directly into your AssistantAgent constructor.

Let your AutoGen agents debate model performance. Give them Arize AI tools to argue with real data, not just opinions.

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 AutoGen

Create your Vinkius account to connect Arize AI to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble Agent Teams for Model Analysis

With AutoGen, you create a team of specialist agents that talk to each other. You could have a 'MonitoringAgent' that uses `get_metrics` to pull performance data from Arize AI. A 'QualityAgent' could use `list_evals` to check for regressions in the latest build. The agents don't just report facts; they debate them. The MonitoringAgent might state, "Accuracy dropped by 3%," and the QualityAgent can respond by triggering a new `run_eval` for 'Hallucination' to see if that's the cause. You get a transcript of their entire diagnostic conversation.

Debate-Driven Incident Response

When a production model acts up, spin up an AutoGen team to figure it out. One agent's job is to establish facts using `get_model` and `list_environments`. Another agent uses `get_metrics` to spot the anomaly. A 'RemediationAgent' can then propose a solution. Here's the thing: they'll argue. One agent might say, "The data drift is high, we should retrain," while another counters, "No, the `ingest_log` shows bad data from an upstream source." This back-and-forth, grounded in real Arize AI data, helps the team converge on the actual root cause.

Assign a Security Agent to Your MCP Server

Design an AutoGen agent that is singularly focused on compliance. Its job is to periodically call `list_evals` and look for any 'PII filtering' reports from Arize AI that have failed. It's a simple, automated watchdog. If it finds a failure, it doesn't just send an alert. It initiates a conversation with a 'DevOpsAgent' in the group chat. The SecurityAgent presents the evidence from Arize, and the team can then discuss and execute a fix. It turns monitoring into a collaborative, automated workflow.

Setup guide

Set up Arize AI MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Arize AI tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Arize AI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Arize AI data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Arize AI_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Arize AI data")
    print(result.messages[-1].content)

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 AutoGen

After installing `autogen-ext[mcp]`, you use the `mcp_server_tools` function with your Vinkius endpoint URL. This function fetches the Arize AI tools and prepares them to be passed directly into your `AssistantAgent` constructor.

Yes, this is a core strength. You can create one agent to fetch metrics from Arize AI using `get_metrics`, and another to run evaluations with `run_eval`. They can then converse and collaborate to diagnose issues based on that shared data.

Each agent in a conversation can be given access to the Arize AI tools. One agent might present data from `get_metrics`. Another agent can then challenge that conclusion by calling `list_evals` to provide conflicting or supporting evidence. The final outcome is a consensus reached after considering multiple data points.

A solid setup is a three-agent team: a 'Monitor' that calls `get_metrics`, a 'Tester' that calls `run_eval`, and a 'UserProxyAgent' that can ask questions or direct their work. This creates a simple but effective group for automated analysis.

The server processes requests for your Arize AI model performance metrics, evaluation results, and structural metadata like spaces and datasets. Access is controlled by your private Vinkius token, and all data is handled within an ephemeral, zero-trust sandbox for each request.

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