How to integrate Honeycomb MCP with Autogen

Connect Autogen to Honeycomb MCP. Investigate latency spikes in production dataset, compare error rates by endpoint today, and more using natural language, with authentication handled for you.

Honeycomb MCP logoHoneycomb MCP
Dcr Oauth

Honeycomb is an observability platform for high-cardinality event data. It helps teams debug production systems fast with rich telemetry analysis.

32 Tools

Introduction

This guide walks you through connecting Honeycomb to AutoGen using the Composio tool router. By the end, you'll have a working Honeycomb agent that can investigate latency spikes in production dataset, compare error rates by endpoint today, find anomalous traces in checkout service through natural language commands.

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

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

Also integrate Honeycomb MCP with

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 Honeycomb
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Honeycomb tools
  • Run a live chat loop where you ask the agent to perform Honeycomb 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 Honeycomb MCP server, and what's possible with it?

The Honeycomb MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Honeycomb account. It provides structured and secure access so your agent can perform Honeycomb operations on your behalf.

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 step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Honeycomb account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
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 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 Honeycomb via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

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 Honeycomb connections to use
5

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 Honeycomb session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["honeycomb_mcp"]
    )
    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 Honeycomb tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

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
7

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 Honeycomb assistant agent with MCP tools
    agent = AssistantAgent(
        name="honeycomb_mcp_assistant",
        description="An AI assistant that helps with Honeycomb 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 Honeycomb tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Honeycomb 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 Honeycomb 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 Honeycomb MCP and AutoGen:

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 Honeycomb session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["honeycomb_mcp"]
    )
    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 Honeycomb assistant agent with MCP tools
        agent = AssistantAgent(
            name="honeycomb_mcp_assistant",
            description="An AI assistant that helps with Honeycomb 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 Honeycomb 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 Honeycomb 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 Honeycomb, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Honeycomb MCP action and event your agent gets out of the box.

Canvas agent invoke

Kick off a single-turn run of the Honeycomb Canvas agent.

Canvas agent poll response

Poll for the result of a previously-issued canvas_agent_invoke call.

Create board

Create a board (dashboard) with query, SLO, and text panels.

Create marker

Creates a marker (a vertical annotation on charts) to mark a point or window in time, such as a deploy, incident, or config change.

Create recipient

Create a notification recipient (email, Slack, PagerDuty, or webhook) so it can be attached to triggers and SLO burn alerts.

Create slo

Create an SLO (Service Level Objective) backed by an auto-created SLI derived column.

Create trigger

Create a trigger that fires alerts when a query result crosses a threshold.

Feedback

Submit feedback about Honeycomb's MCP server to the agentic-intelligence team.

Find columns

Search for columns and calculated fields by intent across one or all datasets in an environment.

Find queries

Search query history and saved queries by intent; returns matching queries with their run PKs.

Get aiconversation

Fetch the full event timeline for a single AI conversation, identified by its OpenTelemetry gen_ai.

Get dataset

Get dataset metadata and its full column schema (columns + calculated fields), sorted by most recent write activity.

Get dataset columns

Get the full column schema for one dataset, with optional sample values for specific columns.

Get environment

Get details for a specific environment, including its dataset list sorted by most recent activity.

Get query results

Retrieve results and metadata from an existing query execution.

Get semconv attribute

Get the full definitions of one or more semantic convention attributes by their exact names.

Get span details

Summarize attributes and their common values observed on spans with a specific name.

Get trace

Retrieve all spans for a specific trace ID and render them as a waterfall.

Get triggers

List triggers (alert rules) for the team, or fetch full configuration for a single trigger.

Get workspace context

Call this tool first to orient yourself in a Honeycomb workspace.

List aiconversations

Discover recent AI agent conversations (gen_ai.

List boards

List boards (saved dashboards) in an environment, or fetch one board's full contents by ID.

List recipients

List all pre-registered notification recipients (email, Slack, PagerDuty, webhook) for the team.

List semconv namespaces

List the top-level semantic convention namespaces available in this team's registry.

List spans

List span names in trace data, ranked by count, with how often each is a trace root and which dataset the count came from.

Refinery docs

Read Honeycomb Refinery documentation.

Run bubbleup

Run BubbleUp analysis to find what makes a selected data subset different from the baseline.

Run query

Run a time-series aggregation query against a Honeycomb dataset and return computed results.

Search semconv

Search the semantic convention registry for attributes matching a query.

Update board

Edit an existing board (dashboard) in place.

Update slo

Update an existing SLO.

Update trigger

Update an existing trigger.

FAQ

Frequently asked questions

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

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 Honeycomb tools.

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

Start with Honeycomb MCP.It takes 30 seconds.

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

Start building