How to integrate Jam MCP with OpenAI Agents SDK

This guide walks you through connecting Jam to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Jam agent that can list your bug reports, analyze videos, inspect console logs, trace network requests, and read transcripts through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Jam account through Composio's Jam MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Jam logoJam
Api Key

Jam is a browser bug reporting and recording platform for capturing issues, console logs, network data, and repro context. Teams use Jam to inspect, organize, and collaborate on bugs faster without long back-and-forth threads.

16 Tools

Introduction

This guide walks you through connecting Jam to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Jam agent that can list your bug reports, analyze videos, inspect console logs, trace network requests, and read transcripts through natural language commands.

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

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

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

The Jam MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Jam account. It provides structured and secure access to your browser bug reports, recordings, and debugging context, so your agent can analyze reported issues, inspect technical evidence, trace user interactions, review visual details, and browse workspace content on your behalf.

  • Bug report investigation: Have your agent review a Jam’s core details, reported issue, user goal, feedback, and technical indicators to understand what went wrong.
  • Console and network analysis: Let the agent inspect console messages, stack traces, failed network requests, HTTP traffic, and WebSocket activity captured with a Jam.
  • User journey reconstruction: Direct your agent to trace clicks, form inputs, submissions, navigation, and scrolling in chronological order.
  • Recording and screenshot review: Instruct your agent to examine screenshots, sample video frames, analyze recordings, and read available speech transcripts for visual and spoken context.
  • Workspace discovery: Have your agent search Jams, folders, members, recording links, submitted reports, and connected recording domains across your workspace.

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

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

Analyze Jam Video

Extract structured user goals, reported issues, feedback, visual observations, interactions, and technical indicators from a video Jam.

Get Console Logs

Get captured browser console errors, warnings, information, debug output, and stack traces from a Jam.

Get Jam Details

Get the core details and debugging context for a Jam.

Get Jam Metadata

Get custom application debugging context attached through the jam.

Get Network Requests

Get captured HTTP requests and WebSocket frames from a Jam, with filters for failures, hosts, methods, content types, and response bodies.

Get Recording Link

Get one Recording Link's settings and submitted-Jam count by public ID.

Get Jam Screenshots

Get screenshots and image attachments from a screenshot-type Jam for visual inspection.

Get User Events

Get the chronological user interaction timeline from a Jam, including clicks, inputs, submissions, navigation, and scrolling.

Get Jam Video Frames

Get still frames from a video Jam as an overview grid, exact timestamps, or an evenly sampled time window.

Get Jam Video Transcript

Get the timestamped WebVTT speech transcript from a microphone-enabled video Jam when available; otherwise return Jam's explanation that it is pending or unavailable.

List Jam Folders

Browse or search one page of workspace folders and return their IDs, names, Jam counts, and timestamps; pass next_cursor as cursor to continue.

List Jams

Search and browse workspace Jams by text, type, folder, author, source URL, or creation date.

List Jam Members

Browse or search one page of workspace members by name or email for author discovery and attribution; pass next_cursor as cursor to continue.

List Recording Domains

List the workspace's connected recording domains and whether each is verified to capture console and network logs.

List Recording Link Jams

List Jams submitted through one Recording Link, newest first.

List Recording Links

List workspace Recording Links newest first, optionally including revoked links.

FAQ

Frequently asked questions

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

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

Start with Jam.It takes 30 seconds.

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

Start building