How to integrate PromptLayer MCP with OpenAI Agents SDK

This guide walks you through connecting PromptLayer to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working PromptLayer agent that can browse your prompt templates, inspect request logs, list registered tools, and review saved workflows through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a PromptLayer account through Composio's PromptLayer MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

PromptLayer logoPromptLayer
Api Key

PromptLayer is a prompt management and observability platform for LLM apps. Use it to version prompts, run evaluations, trace requests, and analyze model behavior.

16 Tools

Introduction

This guide walks you through connecting PromptLayer to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working PromptLayer agent that can browse your prompt templates, inspect request logs, list registered tools, and review saved workflows through natural language commands.

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

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

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

The PromptLayer MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your PromptLayer account. It provides structured and secure access to your prompts, request logs, workflows, tools, skill collections, and tables, so your agent can find prompt templates, inspect LLM activity, browse workflows, review registered resources, and analyze table data on your behalf.

  • Prompt discovery and inspection: Have your agent search prompt templates and retrieve specific versions, messages, model settings, snippets, or release details for review.
  • Request monitoring and analysis: Instruct your agent to search LLM request logs and inspect recorded inputs, outputs, timing, usage, metadata, tags, and scores.
  • Workflow and tool exploration: Let the agent find workflows and registered tools, then retrieve their definitions without running them.
  • Skill and workspace browsing: Direct your agent to browse folders, registry items, and skill collections, including the files stored in a selected collection.
  • Table data review: Have your agent find tables, inspect their sheets and columns, and read rows with optional schema and execution summaries.

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

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

Get Prompt Template

Retrieve a prompt template version, release label, messages, model metadata, snippets, and optionally provider-ready kwargs without executing it.

Get Registered Tool

Retrieve a PromptLayer registered tool definition by ID or name at a selected version or release label without test execution.

Get Request Log

Retrieve one PromptLayer request log with its recorded input, output, timing, usage, metadata, tags, and scores.

Get Skill Collection

Retrieve a PromptLayer skill collection and its files as JSON at a selected version or release label.

Get Table

Retrieve one PromptLayer Table's metadata and per-sheet row counts by UUID.

Get Workflow

Retrieve a PromptLayer workflow definition by ID or name at a specific version or release label without running it.

List Folder Entities

Browse or search PromptLayer folders and registry entities in the API-key workspace, optionally recursively and with metadata.

List Prompt Templates

Search and page through PromptLayer prompt templates and snippets without executing a model.

List Registered Tools

List and filter tools defined in PromptLayer's tool registry without executing them.

List Skill Collections

List and filter PromptLayer skill collections available in the API-key workspace.

List Table Columns

List one page of user and optionally system columns for a PromptLayer Table sheet.

List Table Rows

Read one page of rows and cells from a PromptLayer Table sheet, with optional schema and execution aggregates.

List Tables

Search and page through PromptLayer Tables by folder, name, or referenced prompt.

List Table Sheets

List one page of sheets in a PromptLayer Table, optionally filtering by referenced prompt.

List Workflows

Search and page through PromptLayer workflows without running them.

Search Request Logs

Search PromptLayer request logs by text or structured filters and return one rate-limited page sorted by operational fields.

FAQ

Frequently asked questions

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

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

Start with PromptLayer.It takes 30 seconds.

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

Start building