How to integrate Bugsnag MCP with Pydantic AI

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

Introduction

This guide walks you through connecting Bugsnag to Pydantic AI using the Composio tool router. By the end, you'll have a working Bugsnag agent that can bulk update error statuses for project x, invite new collaborator to my organization, create a saved search for critical errors, delete all errors in the staging project through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Bugsnag account through Composio's Bugsnag 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 Bugsnag
  • 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 Bugsnag 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 Bugsnag MCP server, and what's possible with it?

The Bugsnag MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Bugsnag account. It provides structured and secure access to your error monitoring environment, so your agent can perform actions like managing errors, configuring integrations, inviting collaborators, and customizing project event fields on your behalf.

  • Bulk error management and updates: Let your agent update or clear multiple errors across your projects to streamline incident response and maintenance.
  • Integration configuration and cleanup: Have your agent set up new third-party integrations or remove existing ones, ensuring your Bugsnag projects are always connected to the right tools.
  • User and collaborator management: Easily invite new collaborators to your organization or remove access for old members, keeping your team roster up to date.
  • Custom event field creation and deletion: Direct your agent to add or remove custom event fields for advanced filtering and analytics within your projects.
  • Project-level administration and cleanup: Instruct your agent to perform large-scale actions such as deleting all errors or even entire projects, giving you powerful administrative control when needed.

Supported Tools & Triggers

Tools
Bulk Update ErrorsTool to bulk update multiple errors in a project.
Configure IntegrationTool to configure a new integration for a bugsnag project.
Invite CollaboratorTool to invite a collaborator to an organization.
Create Custom Event FieldTool to create a custom event field for a project.
Create Saved SearchTool to create a new saved search for a project.
Delete All Errors in a ProjectTool to delete all errors in a project.
Delete CollaboratorTool to remove a collaborator from an organization.
Delete a configured integrationTool to delete a configured integration.
Delete Event FieldTool to delete a custom event field.
Delete ProjectTool to delete a project.
Delete Saved SearchTool to delete a saved search.
Get Saved SearchTool to retrieve a saved search by id.
Get Saved Search Usage SummaryTool to get usage summary for a saved search.
List Collaborator Access Details for ProjectsTool to list summary details of the projects a collaborator has access to.
List CollaboratorsTool to list collaborators in an organization.
List Collaborators on ProjectTool to list collaborators on a project.
List Configured Integrations for ProjectTool to list configured integrations for a project.
List Errors on ProjectTool to list all errors in a project.
List Event Fields for ProjectTool to list event fields for a project.
List Events on ProjectTool to list events for a project.
List OrganizationsTool to list organizations for the authenticated user.
List Pivots for ProjectTool to list pivots for a project.
List ProjectsTool to list projects in an organization.
List Release GroupsTool to list release groups for a project.
List ReleasesTool to list releases for a project.
List Saved Searches on ProjectTool to list saved searches for a project.
List Supported IntegrationsTool to list all supported integrations.
List Trends for Project BucketsTool to list trend buckets for a project.
Regenerate Project API KeyTool to regenerate a project's api key.
Show Collaborator Access Details for ProjectTool to show a collaborator's access details for a project.
Show Collaborator on OrganizationTool to show a collaborator in an organization.
Show Collaborator on ProjectTool to show a collaborator in a project.
Update Collaborator PermissionsTool to update a collaborator's project access permissions.

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 Bugsnag
  • 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 Bugsnag
  • MCPServerStreamableHTTP connects to the Bugsnag 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 Bugsnag
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["bugsnag"],
    )
    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 Bugsnag 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
bugsnag_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[bugsnag_mcp],
    instructions=(
        "You are a Bugsnag assistant. Use Bugsnag tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Bugsnag endpoint
  • The agent uses GPT-5 to interpret user commands and perform Bugsnag 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 Bugsnag.\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
  • Bugsnag 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 Bugsnag and Pydantic AI:

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 Bugsnag
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["bugsnag"],
    )
    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
    bugsnag_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[bugsnag_mcp],
        instructions=(
            "You are a Bugsnag assistant. Use Bugsnag 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 Bugsnag.\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 Bugsnag through Composio's Tool Router. With this setup, your agent can perform real Bugsnag 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 + Bugsnag 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 Bugsnag MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Bugsnag MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Bugsnag MCP with Claude Agent SDK

Google ADK

Google ADK

Use Bugsnag MCP with Google ADK

LangChain

LangChain

Use Bugsnag MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Bugsnag MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Bugsnag MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Bugsnag MCP with LlamaIndex

CrewAI

CrewAI

Use Bugsnag MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Bugsnag MCP?

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

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

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

Used by agents from

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