How to Use the Arize AI MCP in CrewAI

Q: How do I let my CrewAI agents access Arize AI metrics?

You include the getmetrics tool in the agent's tool list. The agent will then invoke this tool whenever it needs to assess current model performance.

Deploy a crew of specialized agents in CrewAI to automate Arize AI observability tasks.

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 CrewAI

Create your Vinkius account to connect Arize AI to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized agents for Arize AI

Assign a monitor agent to call `get_metrics` and `list_models` periodically. This agent identifies drifting models and reports findings to the rest of your CrewAI team. Your agents share memory to coordinate actions. When one agent detects a problem, another can use `run_eval` to confirm the issue before taking further steps.

Automating telemetry with CrewAI

Feed raw logs into your platform using `ingest_log`. Your data-focused agents in CrewAI manage the flow of information to ensure your model telemetry is always up to date. Use `list_datasets` to keep your evaluation benchmarks current. The crew handles the discovery of new data so you don't have to manually update your monitoring scripts.

Systematic evaluation via CrewAI

Configure your agents to verify model outputs against Arize AI evaluation runs. By using `list_evals`, your crew knows exactly which tests to apply to different LLM versions. It removes the need for manual oversight. Your CrewAI agents execute the checks, analyze the results, and escalate only when human intervention is required.

Setup guide

Set up Arize AI MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Arize AI tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Arize AI Analyst",
    goal="Access and analyze Arize AI data via MCP.",
    backstory="Expert analyst with direct Arize AI access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Arize AI transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Arize AI Analyst",
        goal="Access and analyze Arize AI data via MCP.",
        backstory="Expert analyst with direct Arize AI access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Arize AI transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You pass the Arize AI MCP server URL directly into your agent's configuration. The agents then treat these tools as native capabilities for their assigned tasks.

You include the `get_metrics` tool in the agent's tool list. The agent will then invoke this tool whenever it needs to assess current model performance.

Yes, you use the tool filter in your CrewAI setup to limit which tools each agent can use. This keeps your agents focused on their specific roles.

Vinkius provides a single endpoint token that handles the connection. You place this in your environment variables, and the MCP server manages the rest.

Your model logs are processed in an ephemeral, isolated environment. Only your configured CrewAI agents can trigger tools to move or read your specific telemetry datasets.

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