How to integrate Honeycomb MCP with OpenAI Agents SDK

Connect OpenAI Agents SDK 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 the OpenAI Agents SDK 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 OpenAI Agents SDK 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 necessary dependencies
  • Initialize Composio and create a Tool Router session for Honeycomb
  • Configure an AI agent that can use Honeycomb as a tool
  • Run a live chat session where you can ask the agent to perform Honeycomb operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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 step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Honeycomb project
  • Some knowledge of Python or Typescript
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
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Honeycomb.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Honeycomb
const session = await composio.create(userId as string, {
  toolkits: ['honeycomb_mcp'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only honeycomb_mcp.
  • The router checks the user's Honeycomb connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Honeycomb.
  • This approach keeps things lightweight and lets the agent request Honeycomb tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Honeycomb. Help users perform Honeycomb operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Honeycomb and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a hostedMcpTool that connects to the MCP server URL we created earlier.
  • The headers object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Honeycomb operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

// Simple CLI
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: 'You: ',
});

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

  if (!text) {
    rl.prompt();
    return;
  }

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Honeycomb.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Honeycomb MCP and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['honeycomb_mcp'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Honeycomb. Help users perform Honeycomb operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

  // Simple CLI
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: ',
  });

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

    if (!text) {
      rl.prompt();
      return;
    }

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

main().catch((err) => {
  console.error('Fatal error:', err);
  process.exit(1);
});

Conclusion

This was a starter code for integrating Honeycomb MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Honeycomb.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
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. OpenAI Agents SDK 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