# How to integrate Phantombuster MCP with OpenAI Agents SDK

```json
{
  "title": "How to integrate Phantombuster MCP with OpenAI Agents SDK",
  "toolkit": "Phantombuster",
  "toolkit_slug": "phantombuster",
  "framework": "OpenAI Agents SDK",
  "framework_slug": "open-ai-agents-sdk",
  "url": "https://composio.dev/toolkits/phantombuster/framework/open-ai-agents-sdk",
  "markdown_url": "https://composio.dev/toolkits/phantombuster/framework/open-ai-agents-sdk.md",
  "updated_at": "2026-05-12T10:21:54.664Z"
}
```

## Introduction

This guide walks you through connecting Phantombuster to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Phantombuster agent that can download agent usage csv for last month, list all active agents in your account, get the country for this ip address through natural language commands.
This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Phantombuster account through Composio's Phantombuster MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Phantombuster with

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

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

The Phantombuster MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Phantombuster account. It provides structured and secure access to your web automation and data extraction tools, so your agent can perform actions like running agents, fetching reports, exporting usage data, and managing your automations on your behalf.
- Agent management and monitoring: Instantly list, audit, or fetch details about all your Phantombuster agents and see which are active, deleted, or grouped together.
- Data extraction and export: Have your agent export detailed usage reports or download CSVs of agent and container activity for analytics and compliance.
- Automation workflow insight: Get visibility into branches, containers, and deployment differences—helping you track automation changes and resource usage.
- Organization and account overview: Let your agent retrieve comprehensive organization information or check current API key associations for security and collaboration.
- IP geolocation support: Enable your agent to look up the physical location of specific IP addresses for auditing or compliance checks.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `PHANTOMBUSTER_ABORT_AGENT_V1` | Abort Agent (v1) | Tool to abort all running instances of an agent using the legacy v1 API. Use when you need to immediately stop an agent's execution. Supports soft abort for graceful shutdown. |
| `PHANTOMBUSTER_DELETE_AGENT` | Delete Agent | Tool to delete an agent by id. Use when you need to remove a PhantomBuster agent. Ensure the agent is not currently running before deletion. |
| `PHANTOMBUSTER_DELETE_LEAD_OBJECTS` | Delete Lead Objects | Tool to delete one or more lead objects from organization storage. Use when you need to remove lead data. Provide either leadObjectId, or both slug and type parameters. |
| `PHANTOMBUSTER_DELETE_LEADS_MANY` | Delete Many Leads | Tool to delete multiple leads from organization storage. Use when you need to bulk delete leads by their IDs. |
| `PHANTOMBUSTER_DELETE_LIST` | Delete List | Tool to delete a storage list by id (Beta). Use when you need to remove a list from organization storage. |
| `PHANTOMBUSTER_DELETE_SCRIPT` | Delete Script | Tool to delete a script by id. Use when you need to remove a specific script from PhantomBuster. Optionally specify a branch and environment to delete a specific version. |
| `PHANTOMBUSTER_GET_AGENT` | Get Agent | Tool to get an agent by its ID. Use when you need to retrieve detailed information about a specific Phantombuster agent, including its configuration, schedule, and execution settings. |
| `PHANTOMBUSTER_GET_AGENT_CONTAINERS` | Get Agent Containers (v1) | Tool to get a list of ended containers for an agent, ordered by date. Use when you need to retrieve the last available output logs from an agent. This is a legacy v1 API endpoint. |
| `PHANTOMBUSTER_GET_AGENT_OUTPUT` | Get Agent Output (v1) | Tool to get incremental data from an agent including console output, status, progress and messages. This is a legacy v1 API endpoint designed for easy incremental data retrieval. Use outputPos to track position. |
| `PHANTOMBUSTER_GET_AGENTS_FETCH_ALL` | Get All Agents | Tool to fetch all agents associated with the current user or organization. Use after validating your Phantombuster API key to list available agents. |
| `PHANTOMBUSTER_GET_AGENTS_FETCH_DELETED` | Get Deleted Agents | Tool to get deleted agents for the current user or organization. Use when you need to audit recently removed agents. |
| `PHANTOMBUSTER_GET_BRANCHES_DIFF` | Get Branches Diff | Tool to get the length difference between the staging and release branch of all scripts. Use when assessing branch changes before deployment. |
| `PHANTOMBUSTER_GET_BRANCHES_FETCH_ALL` | Get All Branches | Tool to fetch all branches associated with the current organization. Use when you need to enumerate every branch across your scripts. |
| `PHANTOMBUSTER_GET_CONTAINERS_FETCH_ALL` | Get Containers Fetch All | Tool to get all containers associated with a specified agent. Use when you need to retrieve every container for a given agent, for monitoring or reporting. |
| `PHANTOMBUSTER_GET_LEADS_BY_LIST` | Get Leads By List | Tool to fetch leads by their list ID. Use when you need to retrieve leads from a specific list with optional pagination and filtering. |
| `PHANTOMBUSTER_GET_LOCATION_IP` | Get IP Location | Tool to retrieve the country of a given or environment IP address. Use when you need to geolocate an IP endpoint. Example: get_location_ip(ip="8.8.8.8") |
| `PHANTOMBUSTER_GET_ORGS_EXPORT_AGENT_USAGE` | Export Agent Usage CSV | Tool to export agent usage CSV for current organization. Use when you need a downloadable report of all agents' run statistics in CSV format. |
| `PHANTOMBUSTER_GET_ORGS_EXPORT_CONTAINER_USAGE` | Export Container Usage CSV | Tool to export container usage CSV for current organization. Use when you need a downloadable CSV report of container execution history up to 6 months; URL expires in 30 days. |
| `PHANTOMBUSTER_GET_ORGS_FETCH` | Get Organization | Tool to fetch current organization details. Use when you need to retrieve the organization associated with the provided API key. |
| `PHANTOMBUSTER_GET_ORGS_FETCH_AGENT_GROUPS` | Get Agent Groups | Tool to get agent groups and order for the current organization. Use when you need to review how agents are grouped and ordered. |
| `PHANTOMBUSTER_GET_ORGS_FETCH_RESOURCES` | Get Organization Resources | Tool to get current organization's resources and usage. Use when you need to monitor quotas. |
| `PHANTOMBUSTER_GET_ORGS_FETCH_RUNNING_CONTAINERS` | Get Org Running Containers | Tool to get the current organization's running containers. Use after listing agents to identify active containers across the organization. |
| `PHANTOMBUSTER_GET_ORG_STORAGE_LISTS_FETCH_ALL` | Get Org Storage Lists Fetch All | Tool to fetch all storage lists for the authenticated organization. Use when you need to enumerate every storage list available (Beta). |
| `PHANTOMBUSTER_GET_SCRIPT` | Get Script | Tool to fetch a script by its unique ID. Use when you need to retrieve detailed metadata about a specific script, including its branches, visibility, and optionally its source code. |
| `PHANTOMBUSTER_GET_SCRIPT_BY_NAME` | Get Script by Name | Tool to retrieve a script by its name from Phantombuster (Legacy v1 API). Use when you need to fetch script metadata or content by name. Supports both JSON (structured) and raw (plain text) response formats. |
| `PHANTOMBUSTER_GET_SCRIPTS_CODE` | Get Script Code | Tool to get the code of a script. Use when you need to retrieve the source code content of a specific script. |
| `PHANTOMBUSTER_GET_SCRIPTS_FETCH_ALL` | Get All Scripts | Tool to fetch all scripts for the current user. Use after authenticating your Phantombuster API key to list scripts without their code bodies. |
| `PHANTOMBUSTER_GET_USER` | Get User Information | Tool to get information about your PhantomBuster account and your agents using the legacy v1 API. Use when you need to check account quotas, remaining resources, or list associated agents. |
| `PHANTOMBUSTER_POST_AGENTS_UNSCHEDULE_ALL` | Unschedule All Agent Launches | Tool to unschedule all scheduled launches for agents. Use when you need to disable every automated agent run organization-wide after verifying your API key. |
| `PHANTOMBUSTER_POST_AI_COMPLETIONS` | Request AI Completion | Tool to request a text completion from the AI module. Use when you need to generate text based on a prompt. |
| `PHANTOMBUSTER_POST_BRANCHES_CREATE` | Create Branch | Tool to create a new branch. Use when you need to isolate updates by creating a separate branch. Use after authenticating with your Phantombuster API key and optionally specifying an organization. |
| `PHANTOMBUSTER_POST_BRANCHES_DELETE` | Delete Branch | Tool to delete a branch by id. Use when you need to remove obsolete or incorrect script branches; ensure the branch exists before calling. |
| `PHANTOMBUSTER_POST_HCAPTCHA` | Solve hCaptcha | Tool to solve an hCaptcha challenge. Use when you need a valid hCaptcha token for form submissions or automation flows. |
| `PHANTOMBUSTER_POST_IDENTITIES_GENERATE_TOKEN` | Generate Identity Token | Tool to generate an identity token for PhantomBuster. Use when you need to create a new identity token for authentication or session management. |
| `PHANTOMBUSTER_POST_ORG_STORAGE_LEADS_SAVE_MANY` | Save Many Leads | Tool to save multiple leads (1-20) to organization storage in a single batch operation (Beta). Use when you need to create or update leads with LinkedIn profile data and optional enrichment fields. |
| `PHANTOMBUSTER_POST_RECAPTCHA` | Solve reCAPTCHA | Tool to solve a reCAPTCHA challenge (v2 or v3). Use when you need a valid reCAPTCHA response token for form submissions or automation. Note: API returns 200 status even on errors; check the error field in the response. |
| `PHANTOMBUSTER_POST_SCRIPTS_VISIBILITY` | Update Script Visibility | Tool to update the visibility of a script. Use when you need to change whether a script is private, public, or open source. |
| `PHANTOMBUSTER_RELEASE_BRANCH` | Release Branch | Tool to release a script branch. Use when you need to deploy a branch to production or release changes to specified scripts. |
| `PHANTOMBUSTER_SAVE_AGENT` | Save Agent | Tool to create a new agent or update an existing one. Use when you need to configure an agent's launch schedule, settings, or behavior. If an agent ID is provided, the existing agent will be updated; otherwise, a new agent is created. |
| `PHANTOMBUSTER_SAVE_AGENT_GROUPS` | Save Agent Groups | Tool to update agent groups and order for the current user's organization. Use when you need to reorganize agents into groups or change their display order. |
| `PHANTOMBUSTER_SAVE_COMPANY_OBJECT` | Save Company Object | Tool to save one company object to the organization storage. Use when you need to create or update a company object with LinkedIn company data and custom properties. |
| `PHANTOMBUSTER_SAVE_COMPANY_OBJECTS_MANY` | Save Many Company Objects | Tool to save many company objects to organization storage. Use when you need to bulk insert or update company data with a minimum of 1 and maximum of 20 objects per request. |
| `PHANTOMBUSTER_SAVE_IDENTITY_EVENT` | Save Identity Event | Tool to save an identity event to Phantombuster. Use when you need to record user interactions or activities associated with specific social media profiles. |
| `PHANTOMBUSTER_SAVE_LEAD` | Save Lead | Tool to save or update a lead in Phantombuster org storage. Use when you need to store LinkedIn profile data or other lead information. |
| `PHANTOMBUSTER_SAVE_LEAD_OBJECT` | Save Lead Object | Tool to save a lead object to organization storage. Use when you need to store or update lead information with custom properties. |
| `PHANTOMBUSTER_SAVE_LEADS_OBJECTS_MANY` | Save Many Lead Objects | Tool to save multiple lead objects to Phantombuster's organization storage. Use when you need to create or update multiple lead objects in a single API call. |
| `PHANTOMBUSTER_SAVE_LIST` | Save List | Tool to save (create or update) a list with filter criteria. Use when you need to create a new list or update an existing one by providing a filter configuration. This is a Beta feature. |
| `PHANTOMBUSTER_SAVE_SCRIPT` | Save Script | Tool to create a new script or update an existing one. Provide an id to update; otherwise creates new script. Use when you need to save JavaScript automation code to Phantombuster. |
| `PHANTOMBUSTER_SEARCH_COMPANY_OBJECTS` | Search Company Objects | Tool to search company objects in Phantombuster's organizational storage. Use when you need to find companies by specific criteria or perform a global search. |
| `PHANTOMBUSTER_SEARCH_LEAD_OBJECTS` | Search Lead Objects | Tool to search lead objects in Phantombuster org storage. Use when you need to find leads based on search criteria or filter conditions. |
| `PHANTOMBUSTER_STOP_AGENT` | Stop Agent | Tool to stop a running agent. Use when you need to halt agent execution, optionally cascading to slave agents or switching to manual launch mode. |
| `PHANTOMBUSTER_UPDATE_SCRIPT` | Update Script (v1 API) | Tool to update an existing script or create a new one if it does not exist (Legacy v1 API). Use when you need to save script code to Phantombuster. If insertOnly is true, the operation will fail if a script with the same name already exists. |
| `PHANTOMBUSTER_UPDATE_SCRIPTS_ACCESS_LIST` | Update Script Access List | Tool to update the access list of a script. Use when you need to add or remove users/orgs from a script's access list in a specific branch. |

## Supported Triggers

None listed.

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

The Phantombuster MCP server is an implementation of the Model Context Protocol that connects your AI agent to Phantombuster. It provides structured and secure access so your agent can perform Phantombuster 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 Phantombuster 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 Phantombuster.
```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 phantombuster.
- The router checks the user's Phantombuster connection and prepares the MCP endpoint.
- The returned session.mcp.url is the MCP URL that your agent will use to access Phantombuster.
- This approach keeps things lightweight and lets the agent request Phantombuster tools only when needed during the conversation.
```python
# Create a Phantombuster Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["phantombuster"]
)

mcp_url = session.mcp.url
```

```typescript
// Create Tool Router session for Phantombuster
const session = await composio.create(userId as string, {
  toolkits: ['phantombuster'],
});
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 Phantombuster. "
        "Help users perform Phantombuster 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 Phantombuster. Help users perform Phantombuster 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=["phantombuster"]
)
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 Phantombuster. "
        "Help users perform Phantombuster 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: ['phantombuster'],
  });
  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 Phantombuster. Help users perform Phantombuster 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 Phantombuster MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Phantombuster.
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 Phantombuster MCP Agent with another framework

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

## Related Toolkits

- [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management.
- [21risk](https://composio.dev/toolkits/_21risk) - 21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters.
- [Abstract](https://composio.dev/toolkits/abstract) - Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions.
- [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows.
- [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations.
- [Anonyflow](https://composio.dev/toolkits/anonyflow) - Anonyflow is a service for encryption-based data anonymization and secure data sharing. It helps organizations meet GDPR, CCPA, and HIPAA data privacy compliance requirements.
- [Api ninjas](https://composio.dev/toolkits/api_ninjas) - Api ninjas offers 120+ public APIs spanning categories like weather, finance, sports, and more. Developers use it to supercharge apps with real-time data and actionable endpoints.
- [Api sports](https://composio.dev/toolkits/api_sports) - Api sports is a comprehensive sports data platform covering 2,000+ competitions with live scores and 15+ years of stats. Instantly access up-to-date sports information for analysis, apps, or chatbots.
- [Apify](https://composio.dev/toolkits/apify) - Apify is a cloud platform for building, deploying, and managing web scraping and automation tools called Actors. It lets you automate data extraction and workflow tasks at scale—no infrastructure headaches.
- [Autom](https://composio.dev/toolkits/autom) - Autom is a lightning-fast search engine results data platform for Google, Bing, and Brave. Developers use it to access fresh, low-latency SERP data on demand.
- [Beaconchain](https://composio.dev/toolkits/beaconchain) - Beaconchain is a real-time analytics platform for Ethereum 2.0's Beacon Chain. It provides detailed insights into validators, blocks, and overall network performance.
- [Big data cloud](https://composio.dev/toolkits/big_data_cloud) - BigDataCloud provides APIs for geolocation, reverse geocoding, and address validation. Instantly access reliable location intelligence to enhance your applications and workflows.
- [Bigpicture io](https://composio.dev/toolkits/bigpicture_io) - BigPicture.io offers APIs for accessing detailed company and profile data. Instantly enrich your applications with up-to-date insights on 20M+ businesses.
- [Bitquery](https://composio.dev/toolkits/bitquery) - Bitquery is a blockchain data platform offering indexed, real-time, and historical data from 40+ blockchains via GraphQL APIs. Get unified, reliable access to complex on-chain data for analytics, trading, and research.
- [Brightdata](https://composio.dev/toolkits/brightdata) - Brightdata is a leading web data platform offering advanced scraping, SERP APIs, and anti-bot tools. It lets you collect public web data at scale, bypassing blocks and friction.
- [Builtwith](https://composio.dev/toolkits/builtwith) - BuiltWith is a web technology profiler that uncovers the technologies powering any website. Gain actionable insights into analytics, hosting, and content management stacks for smarter research and lead generation.
- [Byteforms](https://composio.dev/toolkits/byteforms) - Byteforms is an all-in-one platform for creating forms, managing submissions, and integrating data. It streamlines workflows by centralizing form data collection and automation.
- [Cabinpanda](https://composio.dev/toolkits/cabinpanda) - Cabinpanda is a data collection platform for building and managing online forms. It helps streamline how you gather, organize, and analyze responses.

## Frequently Asked Questions

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

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

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

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

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