How to integrate Arize AX MCP with Pydantic AI

This guide walks you through connecting Arize AX to Pydantic AI using the Composio tool router. By the end, you'll have a working Arize AX agent that can summarize failed spans from latest traces, compare experiment results across prompt versions, create dataset from production traces through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Arize AX account through Composio's Arize AX MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Arize AX logoArize AX
Api Key

Arize AX is an AI engineering platform for tracing, evaluating, and improving AI applications. Use it to debug LLM behavior, compare experiments, and improve production AI quality.

24 Tools

Introduction

This guide walks you through connecting Arize AX to Pydantic AI using the Composio tool router. By the end, you'll have a working Arize AX agent that can summarize failed spans from latest traces, compare experiment results across prompt versions, create dataset from production traces through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Arize AX account through Composio's Arize AX MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Arize AX with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Arize AX
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Arize AX workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

What is the Arize AX MCP server, and what's possible with it?

The Arize AX MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Arize AX account. It provides structured and secure access to your projects, datasets, prompts, experiments, traces, and spans, so your agent can inspect AI activity, manage evaluation data, maintain prompts, run experiments, and review results on your behalf.

  • Project and space discovery: Have your agent find accessible spaces and projects, then retrieve details about the AI applications you monitor.
  • Dataset management: Let the agent create and rename datasets, add or update examples, and review examples from current or named dataset versions.
  • Prompt versioning: Direct your agent to create prompts, publish new immutable versions, update prompt descriptions, and review current or previous versions.
  • Experiment tracking: Instruct your agent to create experiments, append runs, and inspect experiment outputs for evaluation and comparison.
  • Trace and span analysis: Have your agent review bounded sets of traces and spans within chosen time ranges and filters to investigate application behavior.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Arize AX
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Arize AX
  • MCPServerStreamableHTTP connects to the Arize AX MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Arize AX
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["arize_ax"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Arize AX tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
arize_ax_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[arize_ax_mcp],
    instructions=(
        "You are a Arize AX assistant. Use Arize AX tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Arize AX endpoint
  • The agent uses GPT-5 to interpret user commands and perform Arize AX operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Arize AX.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Arize AX API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Arize AX and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Arize AX
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["arize_ax"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    arize_ax_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[arize_ax_mcp],
        instructions=(
            "You are a Arize AX assistant. Use Arize AX tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Arize AX.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Arize AX through Composio's Tool Router. With this setup, your agent can perform real Arize AX actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Arize AX for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

Every Arize AX action and event your agent gets out of the box.

Add Dataset Examples

Append arbitrary-field examples to an Arize dataset or a specified dataset version.

Add Experiment Runs

Append one or more runs to an existing Arize experiment.

Create Dataset

Create an Arize dataset in a space with an explicit initial array of examples.

Create Experiment

Create an Arize experiment with initial runs, associated with exactly one dataset or space.

Create Prompt

Create an Arize prompt and its initial version in a space.

Create Prompt Version

Create a new immutable version of an existing Arize prompt.

Get Dataset

Get one Arize dataset and its versions by dataset ID.

Get Experiment

Get one Arize experiment by its ID, without its experiment runs.

Get Project

Get one accessible Arize project by its ID.

Get Prompt

Get an Arize prompt with its current, explicitly selected, or labeled version.

Get Space

Get one accessible Arize space by its ID.

List Dataset Examples

List one page of examples from an Arize dataset or a specific dataset version, preserving user-defined example fields.

List Datasets

List one page of Arize datasets, optionally filtered by space or dataset name.

List Experiment Runs

List one page of runs and outputs for an Arize experiment, preserving additional run fields.

List Experiments

List one page of Arize experiments, optionally filtered by dataset, space, or name.

List Projects

List one page of accessible Arize projects, optionally filtered by space or project name.

List Prompts

List one page of Arize prompts, optionally filtered by space or prompt name.

List Prompt Versions

List one page of versions for an Arize prompt, newest first.

List Spaces

List one page of Arize spaces accessible to the connected API key, optionally filtered by organization or name.

List Spans

Read one bounded page of spans for an Arize project using optional time and filter constraints.

List Traces

Read one bounded page of traces and nested spans for an Arize project using optional time and filter constraints; nested spans may be truncated per trace.

Update Dataset

Rename an existing Arize dataset.

Update Dataset Examples

Update existing Arize dataset examples by ID, optionally creating a named dataset version.

Update Prompt

Update or clear an Arize prompt's description.

FRAMEWORKS

How to build Arize AX MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Arize AX MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Arize AX MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Arize AX MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Arize AX MCP with Claude Cowork

Codex logo

Codex

Use Arize AX MCP with Codex

OpenClaw logo

OpenClaw

Use Arize AX MCP with OpenClaw

Hermes logo

Hermes

Use Arize AX MCP with Hermes

CLI logo

CLI

Use Arize AX MCP with CLI

Google ADK logo

Google ADK

Use Arize AX MCP with Google ADK

LangChain logo

LangChain

Use Arize AX MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Arize AX MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Arize AX MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Arize AX MCP with LlamaIndex

CrewAI logo

CrewAI

Use Arize AX MCP with CrewAI

FAQ

Frequently asked questions

With a standalone Arize AX MCP server, the agents and LLMs can only access a fixed set of Arize AX tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Arize AX and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Pydantic AI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Arize AX tools.

Yes, absolutely. You can configure which Arize AX scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Arize AX data and credentials are handled as safely as possible.

Start with Arize AX.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Arize AX tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies