How to integrate Lyzr MCP with Pydantic AI

This guide walks you through connecting Lyzr to Pydantic AI using the Composio tool router. By the end, you'll have a working Lyzr agent that can create ai agents, chat with your agents, schedule workflows, manage agent memory, and run ai checks through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Lyzr account through Composio's Lyzr 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
Lyzr logoLyzr
Api Key

Lyzr is an AI agent platform for building, running, evaluating, and managing agents. It helps teams ship safer AI workflows with Studio services for memory, voice, simulations, and knowledge bases.

22 Tools

Introduction

This guide walks you through connecting Lyzr to Pydantic AI using the Composio tool router. By the end, you'll have a working Lyzr agent that can create ai agents, chat with your agents, schedule workflows, manage agent memory, and run ai checks through natural language commands.

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

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

Also integrate Lyzr 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 Lyzr
  • 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 Lyzr 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 Lyzr MCP server, and what's possible with it?

The Lyzr MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Lyzr account. It provides structured and secure access to your agents, memory, knowledge bases, Responsible AI policies, simulations, schedules, workflows, and voice records, so your agent can create and manage agents, run conversations, search stored knowledge, review safety results, and monitor operations on your behalf.

  • Agent creation and conversations: Have your agent create single-task agents with chosen models and instructions, activate or deactivate them, run conversations, inspect their setup, or delete them.
  • Memory and knowledge retrieval: Let the agent store conversation messages, search memories across sessions, clear session history, inspect knowledge bases, and retrieve relevant documents.
  • Responsible AI and simulation review: Direct your agent to review available safety policies, evaluate text for blocks or redactions, and examine simulation performance and reported issues.
  • Schedules and workflow monitoring: Instruct your agent to create, review, or delete scheduled agent runs, then inspect SuperFlow workflows and their execution status.
  • Voice activity review: Have your agent list available voice agents and review call transcripts by agent, session, organization, or date range.

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 Lyzr
  • 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 Lyzr
  • MCPServerStreamableHTTP connects to the Lyzr 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 Lyzr
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["lyzr"],
    )
    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 Lyzr 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
lyzr_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[lyzr_mcp],
    instructions=(
        "You are a Lyzr assistant. Use Lyzr tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Lyzr endpoint
  • The agent uses GPT-5 to interpret user commands and perform Lyzr 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 Lyzr.\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
  • Lyzr 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 Lyzr 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 Lyzr
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["lyzr"],
    )
    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
    lyzr_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[lyzr_mcp],
        instructions=(
            "You are a Lyzr assistant. Use Lyzr 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 Lyzr.\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 Lyzr through Composio's Tool Router. With this setup, your agent can perform real Lyzr 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 + Lyzr 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 Lyzr action and event your agent gets out of the box.

Add Memory Messages

Store a batch of conversation messages in Lyzr Memory for an owner, session, and optional agent, with optional synchronous fact extraction.

Chat With Agent

Send a message or message history to an active Agent Studio agent and return its synchronous inference response for a session.

Clear Memory Session

Permanently clear messages and memories for one explicit owner and session in Lyzr Memory.

Create Agent

Create a single-task Agent Studio agent with an LLM provider, model, instructions, and optional tool configuration.

Create Agent Schedule

Create a cron schedule that runs one Agent Studio agent with a message in a specified timezone.

Delete Agent

Permanently delete one Agent Studio agent by ID.

Delete Agent Schedule

Permanently delete one agent cron schedule and remove its associated scheduler job.

Evaluate Text With RAI Policy

Apply one owned Responsible AI policy to text and return processed text, block decisions, warnings, detections, and redactions.

Get Agent

Return the current configuration and status of one Agent Studio agent by ID.

Get Knowledge Base

Return one Lyzr Knowledge Base configuration by its known RAG configuration ID.

Get Simulation Overview

Return aggregate Agent Simulation counts and average evaluation pass rate for the connected workspace.

List Agents

Return all Agent Studio agents owned by the connected API key, including IDs needed by lifecycle and inference tools.

List Agent Schedules

Return one page of agent cron schedules, optionally filtered by user, agent, or active state.

List Agent Simulation Issues

Return recent performance, error, and Responsible AI issues across monitored agents, optionally filtered by resolution and severity.

List RAI Policies

Return Responsible AI policies owned by the authenticated user, including policy IDs and enabled guardrail configuration.

List SuperFlow Executions

Return one page of SuperFlow execution records, optionally filtered by workflow and execution status.

List SuperFlow Workflows

Return all SuperFlow workflow definitions accessible to the connected API key, including workflow IDs and graph data.

List Voice Agents

Return saved Voice agents accessible to the connected organization, including IDs used to filter transcripts.

List Voice Transcripts

Return one page of accessible Voice call transcripts, optionally filtered by agent, session, organization, or date range.

Retrieve Knowledge

Retrieve relevant documents from a known Lyzr Knowledge Base using configurable basic, MMR, hypothetical-document, or time-aware retrieval.

Search Memories

Semantically search stored memories for one owner, within one session or across that owner's sessions, using Lyzr's hybrid vector and BM25 retrieval.

Set Agent Status

Activate or deactivate an Agent Studio agent.

FRAMEWORKS

How to build Lyzr MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Lyzr MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Lyzr MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Lyzr MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Lyzr MCP with Claude Cowork

Codex logo

Codex

Use Lyzr MCP with Codex

OpenClaw logo

OpenClaw

Use Lyzr MCP with OpenClaw

Hermes logo

Hermes

Use Lyzr MCP with Hermes

CLI logo

CLI

Use Lyzr MCP with CLI

Google ADK logo

Google ADK

Use Lyzr MCP with Google ADK

LangChain logo

LangChain

Use Lyzr MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Lyzr MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Lyzr MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Lyzr MCP with LlamaIndex

CrewAI logo

CrewAI

Use Lyzr MCP with CrewAI

FAQ

Frequently asked questions

With a standalone Lyzr MCP server, the agents and LLMs can only access a fixed set of Lyzr tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Lyzr 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 Lyzr tools.

Yes, absolutely. You can configure which Lyzr 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 Lyzr data and credentials are handled as safely as possible.

Start with Lyzr.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Lyzr 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