How to integrate Bugsnag MCP with Autogen

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

Introduction

This guide walks you through connecting Bugsnag to AutoGen 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 AutoGen 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:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Bugsnag
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Bugsnag tools
  • Run a live chat loop where you ask the agent to perform Bugsnag operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Bugsnag account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

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 python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Bugsnag via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Bugsnag connections to use

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Bugsnag session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["bugsnag"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Bugsnag tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Bugsnag assistant agent with MCP tools
    agent = AssistantAgent(
        name="bugsnag_assistant",
        description="An AI assistant that helps with Bugsnag operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Bugsnag tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Bugsnag related question or task to the agent.\n")

# Conversation loop
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")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Bugsnag tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Bugsnag and AutoGen:

import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Bugsnag session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["bugsnag"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Bugsnag assistant agent with MCP tools
        agent = AssistantAgent(
            name="bugsnag_assistant",
            description="An AI assistant that helps with Bugsnag operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Bugsnag related question or task to the agent.\n")

        # Conversation loop
        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")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

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

Conclusion

You now have an Autogen assistant wired into Bugsnag through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Bugsnag, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

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 Autogen?

Yes, you can. Autogen 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