How to integrate Openlayer MCP with OpenAI Agents SDK

This guide walks you through connecting Openlayer to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Openlayer agent that can list your projects, inspect project versions, review test results, find failing tests, and check data sources through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Openlayer account through Composio's Openlayer MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Openlayer logoOpenlayer
Api Key

Openlayer is an AI quality platform for managing projects, monitoring production data, evaluating tests, and inspecting model performance. Use it to catch regressions, track production quality, and keep AI applications reliable before and after release.

10 Tools

Introduction

This guide walks you through connecting Openlayer to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Openlayer agent that can list your projects, inspect project versions, review test results, find failing tests, and check data sources through natural language commands.

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

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

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

The Openlayer MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Openlayer account. It provides structured and secure access to your projects, versions, monitoring data sources, tests, results, and workspace details, so your agent can review projects, inspect model versions, check monitoring status, analyze test outcomes, and track workspace usage on your behalf.

  • Project and version reviews: Have your agent list Openlayer projects, inspect their versions, and compare processing status and passing, failing, and total test counts.
  • Production monitoring checks: Let the agent find monitoring data sources and review their backend, monitoring status, record counts, and test counts.
  • Test configuration discovery: Direct your agent to list tests for a project and narrow them by category, archive state, origin, production data use, or suggested status.
  • Test result analysis: Instruct your agent to review results for project versions, monitoring data sources, or individual tests, including execution status and available generated insights.
  • Workspace usage visibility: Have your agent check workspace status, connected account membership, usage counts, and current plan limits.

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

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

Get Data Source

Return one Openlayer monitoring data source, including its backend, monitoring status, record and test counts, and optional project or workspace details.

Get Project Version

Return one Openlayer project commit or version with its processing status, commit metadata, storage URI, and passing, failing, and total test counts.

Get Workspace

Return a workspace's identity, status, connected-account membership, usage counts, and plan limits.

List Data Sources

Return one page of monitoring data sources for an Openlayer project, optionally filtered by name.

List Data Source Test Results

Return one page of the latest monitoring test results for an Openlayer data source, optionally filtered by test category or execution status.

List Projects

Return one page of projects visible to the connected Openlayer workspace, optionally filtered by name or task type.

List Project Versions

Return one page of commits and versions for an Openlayer project, including processing status, commit metadata, and passing, failing, and total test counts.

List Project Version Test Results

Return one page of test results for a project version, optionally filtered by test category, archive state, or result status.

List Test Results

Return one page of results for a test, with optional project-version, data-source, and status filters and optional generated insights.

List Tests

Return one page of tests configured for an Openlayer project, with filters for category, archive state, origin version, production-data use, and suggested status.

FAQ

Frequently asked questions

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

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

Start with Openlayer.It takes 30 seconds.

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

Start building