# How to integrate Leverly MCP with OpenAI Agents SDK

```json
{
  "title": "How to integrate Leverly MCP with OpenAI Agents SDK",
  "toolkit": "Leverly",
  "toolkit_slug": "leverly",
  "framework": "OpenAI Agents SDK",
  "framework_slug": "open-ai-agents-sdk",
  "url": "https://composio.dev/toolkits/leverly/framework/open-ai-agents-sdk",
  "markdown_url": "https://composio.dev/toolkits/leverly/framework/open-ai-agents-sdk.md",
  "updated_at": "2026-10-12T12:44:42.418Z"
}
```

## Introduction

This guide walks you through connecting Leverly to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Leverly agent that can show all current ingestion reattempts, stop reattempts for a specific lead, list reattempts history for lead 1234 through natural language commands.
This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Leverly account through Composio's Leverly MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Leverly with

- [Claude Code](https://composio.dev/toolkits/leverly/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/leverly/framework/claude-cowork)
- [Claude Agent SDK](https://composio.dev/toolkits/leverly/framework/claude-agents-sdk)
- [Codex](https://composio.dev/toolkits/leverly/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/leverly/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/leverly/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/leverly/framework/atomic-agent)
- [Google ADK](https://composio.dev/toolkits/leverly/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/leverly/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/leverly/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/leverly/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/leverly/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/leverly/framework/crew-ai)
- [Pydantic AI](https://composio.dev/toolkits/leverly/framework/pydantic-ai)
- [AutoGen](https://composio.dev/toolkits/leverly/framework/autogen)

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

The Leverly MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Leverly account. It provides structured and secure access to your Leverly workflows, so your agent can perform actions like listing reattempt histories, stopping ongoing reattempts, and streamlining automation management on your behalf.
- View reattempt history: Quickly ask your agent to retrieve a complete list of all ingestion reattempts for easy review and troubleshooting.
- Stop ongoing reattempts: Direct your agent to halt any ongoing reattempts for specific leads by providing the relevant reattempt ID.
- Monitor workflow automation: Let your agent inspect and keep tabs on the status of automated processes, ensuring nothing falls through the cracks.
- Accelerate process interventions: Empower your agent to step in and manage exceptions or stuck workflows by stopping unnecessary retries as needed.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `LEVERLY_CREATE_CALL` | Create Call | Tool to create a new call/lead in Leverly system. Sends lead information to trigger an instant phone call to your sales team. Use when integrating external systems (CRM, forms, lead providers) with Leverly. |
| `LEVERLY_LIST_REATTEMPTS` | List Reattempts | Tool to list all reattempts in Leverly. Use when you need to inspect the history of ingestion reattempts before taking further action. |
| `LEVERLY_STOP_REATTEMPTS` | Stop Leverly Reattempts | Tool to stop ongoing reattempts for a lead in Leverly. Use when you need to halt retries for a given reattempt ID. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Leverly MCP server is an implementation of the Model Context Protocol that connects your AI agent to Leverly. It provides structured and secure access so your agent can perform Leverly operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before starting, make sure you have:
- Composio API Key and OpenAI API Key
- Primary know-how of OpenAI Agents SDK
- A live Leverly project
- Some knowledge of Python or Typescript

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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
- Log in to the [Composio dashboard](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Go to Settings and copy your API key.

### 2. Install dependencies

Install the Composio SDK and the OpenAI Agents SDK.
```python
pip install composio_openai_agents openai-agents python-dotenv
```

```typescript
npm install @composio/openai-agents @openai/agents dotenv
```

### 3. Set up environment variables

Create a .env file and add your OpenAI and Composio API keys.
```bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com
```

### 4. Import dependencies

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 Leverly.
```python
import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
```

```typescript
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';
```

### 5. Set up the Composio instance

No description provided.
```python
load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
```

```typescript
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(),
});
```

### 6. Create a Tool Router session

What is happening:
- You give the Tool Router the user id and the toolkits you want available. Here, it is only leverly.
- The router checks the user's Leverly connection and prepares the MCP endpoint.
- The returned session.mcp.url is the MCP URL that your agent will use to access Leverly.
- This approach keeps things lightweight and lets the agent request Leverly tools only when needed during the conversation.
```python
# Create a Leverly Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["leverly"]
)

mcp_url = session.mcp.url
```

```typescript
// Create Tool Router session for Leverly
const session = await composio.create(userId as string, {
  toolkits: ['leverly'],
});
const mcpUrl = session.mcp.url;
```

### 7. Configure the agent

No description provided.
```python
# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Leverly. "
        "Help users perform Leverly operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
```

```typescript
// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Leverly. Help users perform Leverly operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
```

### 8. Start chat loop and handle conversation

No description provided.
```python
print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
```

```typescript
// 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);
});
```

## Complete Code

```python
import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["leverly"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Leverly. "
        "Help users perform Leverly operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
```

```typescript
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: ['leverly'],
  });
  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 Leverly. Help users perform Leverly 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 Leverly MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Leverly.
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.

## How to build Leverly MCP Agent with another framework

- [Claude Code](https://composio.dev/toolkits/leverly/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/leverly/framework/claude-cowork)
- [Claude Agent SDK](https://composio.dev/toolkits/leverly/framework/claude-agents-sdk)
- [Codex](https://composio.dev/toolkits/leverly/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/leverly/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/leverly/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/leverly/framework/atomic-agent)
- [Google ADK](https://composio.dev/toolkits/leverly/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/leverly/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/leverly/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/leverly/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/leverly/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/leverly/framework/crew-ai)
- [Pydantic AI](https://composio.dev/toolkits/leverly/framework/pydantic-ai)
- [AutoGen](https://composio.dev/toolkits/leverly/framework/autogen)

## Related Toolkits

- [0CodeKit](https://composio.dev/toolkits/0codekit) - 0CodeKit is a utility API platform for AI, document, image, and data workflows. Use it to convert, validate, generate, store, and automate data without custom backend code.
- [Airtop](https://composio.dev/toolkits/airtop) - Airtop is a cloud browser platform for AI-powered web automation. Use it to navigate sites, extract data, and run reusable browser workflows.
- [Apify MCP](https://composio.dev/toolkits/apify_mcp) - Apify MCP is the official MCP server for Apify's web scraping and browser automation platform. Use it to run actors, collect structured web data, and automate crawling workflows.
- [Apilio](https://composio.dev/toolkits/apilio) - Apilio is a home automation platform that lets you connect and control smart devices from different brands. It helps you build flexible automations with complex conditions, schedules, and integrations.
- [Basin](https://composio.dev/toolkits/basin) - Basin is a no-code form backend for quickly setting up reliable contact forms. It lets you collect and manage form submissions without writing any server-side code.
- [Bika.ai](https://composio.dev/toolkits/bika) - Bika.ai is an AI automation database platform for managing spaces, teams, records, automations, and outgoing webhooks. It helps teams organize structured data and automate database-driven workflows in one place.
- [Botster](https://composio.dev/toolkits/botster) - Botster is a web automation service for running configurable data collection bots. Use it to collect structured web data without building and maintaining scrapers yourself.
- [Bouncer](https://composio.dev/toolkits/bouncer) - Bouncer is an email validation platform that verifies the authenticity of email addresses in real-time and batch. It helps boost deliverability and reduce bounce rates for your communications.
- [BrowserAct](https://composio.dev/toolkits/browseract) - BrowserAct is a hosted browser-automation service for running web workflows. Use it to execute repeatable browser tasks with templates, proxies, and APIs.
- [Celigo](https://composio.dev/toolkits/celigo) - Celigo is an integration platform as a service for connecting apps, data, and business workflows. It helps teams automate cross-system processes without building every integration from scratch.
- [CheckFlow](https://composio.dev/toolkits/checkflow) - CheckFlow is a workflow and checklist platform for repeatable processes, tasks, templates, teams, data sets, and automation. Use it to standardize operations, track process execution, and keep teams aligned.
- [Conveyor](https://composio.dev/toolkits/conveyor) - Conveyor is a platform that automates security reviews with a Trust Center and AI-driven questionnaire automation. It streamlines compliance and vendor security processes for faster, hassle-free reviews.
- [CrewAI](https://composio.dev/toolkits/crew_ai) - CrewAI is a platform for running deployed automations and managing AMP control-plane resources. Use it to automate workflows and centrally control SaaS automation resources.
- [Cronfree Time Scheduler](https://composio.dev/toolkits/cronfree_time_scheduler) - Cronfree Time Scheduler is an API-based scheduler for recurring webhook calls. Use it to create and remove timezone-aware schedules without running cron.
- [Crowdin](https://composio.dev/toolkits/crowdin) - Crowdin is a localization management platform that streamlines translation workflows and collaboration. It helps teams centralize multilingual content, boost productivity, and automate translation processes.
- [Databox](https://composio.dev/toolkits/databox) - Databox is a business analytics platform that connects your data from any tool and device. It helps you track KPIs, build dashboards, and discover actionable insights.
- [Detrack](https://composio.dev/toolkits/detrack) - Detrack is a delivery management platform for real-time tracking and proof of delivery. It helps businesses automate notifications and keep customers updated every step of the way.
- [Dify](https://composio.dev/toolkits/dify) - Dify is a platform for running and managing published workflow apps via a Service API. Use it to execute workflows and inspect configuration and run history quickly.
- [Digital Humani](https://composio.dev/toolkits/digital_humani) - Digital Humani is a reforestation API for browsing planting projects, submitting tree requests, and tracking planted trees. It helps teams connect climate action directly to products, campaigns, and customer experiences.
- [Dnsfilter](https://composio.dev/toolkits/dnsfilter) - Dnsfilter is a cloud-based DNS security and content filtering solution. It helps organizations block online threats and manage safe internet access with ease.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Leverly MCP?

With a standalone Leverly MCP server, the agents and LLMs can only access a fixed set of Leverly tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Leverly and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with OpenAI Agents SDK?

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 Leverly tools.

### Can I manage the permissions and scopes for Leverly while using Tool Router?

Yes, absolutely. You can configure which Leverly 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.

### How safe is my data with Composio Tool Router?

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 Leverly data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)