How to integrate Avoma MCP with OpenAI Agents SDK

This guide walks you through connecting Avoma to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Avoma agent that can summarize yesterday's customer call notes, find meetings needing follow-up emails, review sales scorecards from this week through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Avoma account through Composio's Avoma MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Avoma logoAvoma
Api Key

Avoma is an AI meeting assistant for recording, transcribing, analyzing, and managing meetings, calls, notes, scorecards, and conversation intelligence. It helps teams turn conversations into searchable notes, follow-ups, coaching insights, and revenue intelligence.

16 Tools

Introduction

This guide walks you through connecting Avoma to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Avoma agent that can summarize yesterday's customer call notes, find meetings needing follow-up emails, review sales scorecards from this week through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Avoma account through Composio's Avoma MCP server.

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

Also integrate Avoma 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 Avoma
  • Configure an AI agent that can use Avoma as a tool
  • Run a live chat session where you can ask the agent to perform Avoma 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 Avoma MCP server, and what's possible with it?

The Avoma MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Avoma account. It provides structured and secure access to your meetings, calls, transcripts, notes, recordings, and conversation intelligence, so your agent can find meetings, retrieve transcripts, review AI insights, analyze engagement, and inspect scorecard evaluations on your behalf.

  • Meeting and call discovery: Have your agent find meetings and externally recorded calls by date, attendee, direction, CRM details, call type, privacy context, or duration.
  • Transcripts, notes, and snippets: Let the agent retrieve full meeting transcripts, review notes in JSON, HTML, or Markdown, and find user-created or AI-generated snippets.
  • Conversation analysis: Direct your agent to review AI insights, topics, speaker segments, sentiment records, and recording access for processed meetings.
  • Engagement and coaching insights: Instruct your agent to summarize team engagement metrics and inspect scorecard evaluations by date, meeting, scorecard, or evaluated user.
  • Call ingestion and workspace review: Have your agent submit externally hosted call recordings for processing, check their status, list visible users and configuration catalogs, or audit active webhook subscriptions.

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 Avoma 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 Avoma.
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 Avoma
const session = await composio.create(userId as string, {
  toolkits: ['avoma'],
});
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 avoma.
  • The router checks the user's Avoma connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Avoma.
  • This approach keeps things lightweight and lets the agent request Avoma 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 Avoma. Help users perform Avoma 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 Avoma 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 Avoma 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 Avoma.
  • 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 Avoma 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: ['avoma'],
  });
  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 Avoma. Help users perform Avoma 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 Avoma MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Avoma.

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 Avoma action and event your agent gets out of the box.

Create Call

Submit an externally hosted call recording to Avoma for asynchronous processing.

Get Call

Retrieve one externally ingested Avoma call by the dialer system's external ID.

Get Engagement Summary

Aggregate Avoma engagement metrics across visible users for a required UTC date range and optional meeting and user filters.

Get Meeting

Retrieve one meeting by UUID, including processing/readiness state and optionally CRM associations.

Get Meeting Analysis

Return Avoma's AI insights, topical and speaker segments, and sentiment records for one processed meeting in a single read-only invocation.

Get Recording

Get time-limited audio and video URLs for a meeting recording.

List Calls

List externally ingested calls in a required UTC date range, optionally filtered by inbound or outbound direction.

List Configuration Resources

List one Avoma configuration catalog: custom categories, smart categories, scorecards, templates, meeting types, or meeting outcomes.

List Engagement Metrics

List per-user Avoma engagement metrics over a required UTC date range with meeting and user filters.

List Meetings

Find meetings visible to the connected Avoma user within a required UTC date range, with optional attendee, CRM, call-type, privacy-context, duration, and ordering filters.

List Notes

Retrieve Avoma notes for meetings in a required UTC date range, optionally narrowed to a meeting or custom category and rendered as JSON, HTML, or Markdown.

List Scorecard Evaluations

List Avoma scorecard evaluations, optionally filtered by UTC date range, scorecard templates, meeting, or evaluated users.

List Snippets

Find user-created or AI-generated meeting snippets by meeting UUID or by a UTC date range of at most 180 days.

List Transcriptions

Find full meeting transcriptions by meeting UUID or by a UTC date range, with attendee and CRM filters.

List Users

Return users visible in the Avoma organization, including their UUID, email, role, teams, and active status.

List Webhooks

Audit the connected organization's active Avoma webhook subscriptions without reading signing secrets.

FAQ

Frequently asked questions

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

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

Start with Avoma.It takes 30 seconds.

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

Start building