How to Use the Arize AI MCP in AutoGen

Q: Does this require a lot of custom code to connect?

No, the autogen-ext package simplifies it. You use a helper function to get the tools from the MCP server URL. The tool adapter handles the schema conversions, so you can just pass the tool list directly to your AssistantAgent.

Let your AutoGen agents debate and solve ML model issues. Connect multiple AI perspectives to your Arize AI observability data.

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

Multi-Agent Model Debugging

Set up a team of agents to troubleshoot a model. One agent, the "Analyst," uses `list_experiments` and `list_spans` to find anomalies in Arize AI. Another agent, the "Engineer," proposes a fix based on the data. They don't just execute a plan; they converse. The Analyst might challenge the Engineer's hypothesis, using data from `get_model` as evidence. This debate leads to a better, more robust solution than a single agent could find.

Consensus-Driven Model Promotion with your MCP Server

Automate your release process with an agent debate. A "QA Agent" can use `list_datasets` to check a new model against a golden dataset in Arize AI. A "Performance Agent" checks its latency and prediction quality with `get_model`. The agents then discuss the results. If QA finds data drift but Performance sees an improvement, they negotiate a course of action. The final decision to promote the model is based on consensus, not a simple script.

Proactive Risk and Performance Audits

Don't wait for things to break. Assign an agent to continuously monitor your models using the Arize AI tools. It can periodically run `list_projects` and `list_experiments` to look for negative trends. When it finds something, it doesn't just send an alert. It initiates a conversation with other agents to diagnose the problem. This turns passive monitoring into an active, collaborative investigation, handled entirely by your AutoGen team.

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

You equip each agent in your group chat with the Arize AI tools. For example, a "MonitoringAgent" can call `list_experiments`, and when it finds an issue, it can present the data to a "DebugAgent," which then uses `list_spans` to investigate further.

Yes. You could have a "DataCurator" agent whose job is to validate and register new datasets. It would use its own logic to inspect data and then call `create_dataset` in Arize AI once it's satisfied with the quality.

The key advantage is collaborative problem-solving. Instead of a single agent following a fixed script, multiple AutoGen agents can debate the data from Arize AI, challenge each other's findings, and arrive at a more reliable conclusion for complex model issues.

No, the `autogen-ext` package simplifies it. You use a helper function to get the tools from the MCP server URL. The tool adapter handles the schema conversions, so you can just pass the tool list directly to your AssistantAgent.

Yes. Your authentication token secures all communication between your AutoGen agents and the server. The server instance handling your requests for model details, experiment lists, and span data runs in a zero-trust, ephemeral sandbox on Vinkius, ensuring your data isn't persisted or exposed.

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