How to integrate PredictLeads MCP with OpenAI Agents SDK

This guide walks you through connecting PredictLeads to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working PredictLeads agent that can discover companies, find similar companies, search technologies, and review company intelligence through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a PredictLeads account through Composio's PredictLeads MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

PredictLeads logoPredictLeads
Api Key

PredictLeads is a company intelligence API for hiring, technology, funding, news, product, and connection data. Use it to spot growth signals and enrich sales, research, and market workflows with fresh company context.

9 Tools

Introduction

This guide walks you through connecting PredictLeads to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working PredictLeads agent that can discover companies, find similar companies, search technologies, and review company intelligence through natural language commands.

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

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

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

The PredictLeads MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your PredictLeads account. It provides structured and secure access to company profiles, hiring activity, technology adoption, financing, news, products, and business connections, so your agent can discover companies, research growth signals, compare similar businesses, search technologies, and monitor followed companies on your behalf.

  • Target company discovery: Have your agent find companies that match specific firmographic criteria and gather extended profiles for sales research.
  • Company intelligence research: Direct your agent to retrieve company details and investigate hiring, technology detections, news, financing, regulatory filings, business connections, website changes, repositories, and products.
  • Growth signal discovery: Let the agent search across companies for job openings, technology adoption, news, financing, investor portfolio connections, products, and startup platform posts.
  • Market and competitor analysis: Instruct your agent to find businesses similar to a chosen company and search the tracked technology catalog by name.
  • Account and company monitoring: Have your agent review followed companies and check your PredictLeads subscription status, monthly credit quota, and credit usage.

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

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

Discover Companies

Find companies using firmographic filters.

Discover Intelligence

Discover one page of jobs, technology adoption, news, financing, investor portfolio connections, products, or startup-platform posts across companies.

Get API Subscription

Check PredictLeads subscription status, monthly credit quota, and credits used.

Get Company

Retrieve one company by PredictLeads UUID or bare domain.

Get Company Intelligence

Retrieve one page of a company's jobs, technology detections, news, financing, SEC filings, connections, website changes, GitHub repositories, or products.

Get Intelligence Record

Retrieve one job opening, extended technology detection, technology, news event, SEC filing, or product by identifier.

Get Similar Companies

Find one page of companies similar to a specified PredictLeads company UUID or domain.

List Followed Companies

List one page of companies already followed for PredictLeads webhook updates.

Search Technologies

Search PredictLeads' tracked technology catalog by fuzzy name.

FAQ

Frequently asked questions

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

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

Start with PredictLeads.It takes 30 seconds.

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

Start building