How to integrate Better stack MCP with Pydantic AI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Better stack Logo
Pydantic AI Logo
divider

Introduction

This guide walks you through connecting Better stack to Pydantic AI using the Composio tool router. By the end, you'll have a working Better stack agent that can show uptime percentage for api monitor, create escalation policy for on-call team, list heartbeat availability for last week, delete unused source group from logging through natural language commands.

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

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

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 Better stack
  • 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 Better stack 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 Better stack MCP server, and what's possible with it?

The Better stack MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Better Stack account. It provides structured and secure access to your monitoring, logging, and incident management tools, so your agent can perform actions like retrieving uptime metrics, managing escalation policies, checking heartbeat statuses, and organizing log sources on your behalf.

  • Monitor health checks and availability: Let your agent fetch uptime percentages, availability summaries, and incident details for any monitor in your stack.
  • Automated escalation policy management: Instruct your agent to create or delete escalation policies, keeping your incident response workflows up-to-date without manual effort.
  • Heartbeat tracking and organization: Have your agent fetch specific heartbeat data, check heartbeat availability, or group related heartbeats for easier monitoring.
  • Log source grouping and management: Enable your agent to create or delete source groups, helping you organize log streams and maintain a tidy observability structure.
  • Webhook integration setup: Direct your agent to register outgoing webhooks so your stack can notify external systems of important events automatically.

Supported Tools & Triggers

Tools
Create Escalation PolicyTool to create a new escalation policy.
Create Heartbeat GroupTool to create a new heartbeat group.
Create Outgoing Webhook IntegrationTool to create a new outgoing webhook integration.
Create Source GroupTool to create a new source group.
Delete Escalation PolicyTool to delete an escalation policy by id.
Delete Source GroupTool to delete a source group by id.
Get HeartbeatTool to get a single heartbeat by id.
Get Heartbeat AvailabilityTool to retrieve availability summary for a specific heartbeat.
Get MonitorTool to get a single monitor.
Get Monitor AvailabilityTool to return an availability summary for a specific monitor.
Get Monitor Response TimesTool to return response times for a specific monitor.
Get Status PageTool to get a single status page by id.
Get Telemetry API TokenTool to retrieve the telemetry api token from the integration configuration.
Get Uptime API TokenTool to retrieve the configured uptime api token.
List Catalog RelationsTool to list all catalog relations.
List Google Monitoring IntegrationsTool to list all google monitoring integrations.
List Grafana IntegrationsTool to list all grafana integrations.
List HeartbeatsTool to list all heartbeats.
List MonitorsTool to list all monitors.
List New Relic IntegrationsTool to list new relic integrations.
List On-Call SchedulesTool to list all on-call schedules.
List Status Page ReportsTool to list all reports on a status page.
List Status PagesTool to list all your status pages.
Update HeartbeatTool to update an existing heartbeat configuration.
Update Heartbeat GroupTool to update an existing heartbeat group.
Update Source GroupTool to update an existing source group.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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

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

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.

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 Better stack
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file

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

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 Better stack
  • MCPServerStreamableHTTP connects to the Better stack MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant

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 Better stack
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["better_stack"],
    )
    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 Better stack 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

Initialize the Pydantic AI Agent

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

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 Better stack.\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
  • Better stack API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns

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 Better stack 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 Better stack
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["better_stack"],
    )
    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
    better_stack_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[better_stack_mcp],
        instructions=(
            "You are a Better stack assistant. Use Better stack 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 Better stack.\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 Better stack through Composio's Tool Router. With this setup, your agent can perform real Better stack 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 + Better stack for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.

How to build Better stack MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Better stack MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Better stack MCP with Claude Agent SDK

Google ADK

Google ADK

Use Better stack MCP with Google ADK

LangChain

LangChain

Use Better stack MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Better stack MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Better stack MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Better stack MCP with LlamaIndex

CrewAI

CrewAI

Use Better stack MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Better stack MCP?

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

Can I use Tool Router MCP with Pydantic AI?

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 Better stack tools.

Can I manage the permissions and scopes for Better stack while using Tool Router?

Yes, absolutely. You can configure which Better stack 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.

How safe is my data with Composio Tool Router?

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 Better stack data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free