# How to integrate Supportbee MCP with OpenAI Agents SDK

```json
{
  "title": "How to integrate Supportbee MCP with OpenAI Agents SDK",
  "toolkit": "Supportbee",
  "toolkit_slug": "supportbee",
  "framework": "OpenAI Agents SDK",
  "framework_slug": "open-ai-agents-sdk",
  "url": "https://composio.dev/toolkits/supportbee/framework/open-ai-agents-sdk",
  "markdown_url": "https://composio.dev/toolkits/supportbee/framework/open-ai-agents-sdk.md",
  "updated_at": "2026-05-12T10:27:33.636Z"
}
```

## Introduction

This guide walks you through connecting Supportbee to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Supportbee agent that can archive all tickets resolved this week, assign new tickets to the support team, create a reusable snippet for refund replies through natural language commands.
This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Supportbee account through Composio's Supportbee MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Supportbee with

- [Claude Agent SDK](https://composio.dev/toolkits/supportbee/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/supportbee/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/supportbee/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/supportbee/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/supportbee/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/supportbee/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/supportbee/framework/cli)
- [Google ADK](https://composio.dev/toolkits/supportbee/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/supportbee/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/supportbee/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/supportbee/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/supportbee/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/supportbee/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 Supportbee
- Configure an AI agent that can use Supportbee as a tool
- Run a live chat session where you can ask the agent to perform Supportbee 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 Supportbee MCP server, and what's possible with it?

The Supportbee MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Supportbee account. It provides structured and secure access to your support ticketing system, so your agent can perform actions like creating and replying to tickets, managing team assignments, organizing tickets, and automating support workflows on your behalf.
- Automated ticket creation and updates: Instantly open new support tickets, update their content, or post replies to customer inquiries without leaving your workflow.
- Team assignment and ticket routing: Direct your agent to assign tickets to the right team or agent, ensuring every request is handled by the appropriate group.
- Archiving and deleting tickets: Keep your helpdesk organized by having the agent archive resolved tickets or permanently remove unwanted ones from the system.
- Reusable response snippets: Let your agent create, manage, and delete response templates so your team can reply faster and more consistently.
- Rule-based workflow automation: Empower your agent to create new automation rules that streamline ticket routing, escalation, and handling based on custom conditions.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `SUPPORTBEE_ADD_LABEL_TO_TICKET` | Add Label to Ticket | Tool to add a label to a ticket. Use when you need to categorize or tag a ticket with a specific label. The label must already exist in your SupportBee account before adding it to a ticket. |
| `SUPPORTBEE_ARCHIVE_TICKET` | Archive SupportBee Ticket | Tool to archive a SupportBee ticket by its ID. Use when you want to move resolved tickets to the archive. |
| `SUPPORTBEE_ASSIGN_TICKET_TO_TEAM` | Assign Ticket to Team | Assigns a ticket to a team in SupportBee. Use when you need to route a support ticket to a specific team for handling. Note: If the ticket is already assigned to a team and a user, reassigning to another team will remove the user assignee. |
| `SUPPORTBEE_CREATE_COMMENT` | Create Ticket Comment | Creates an internal comment on a ticket in SupportBee. Comments are private notes visible only to agents, not to customers. Use this to add internal notes, observations, or collaborate with team members on a ticket. |
| `SUPPORTBEE_CREATE_CONSEQUENCE` | Create Consequence | Creates a new consequence for rules automation in SupportBee. Use when setting up automated actions that should be triggered by rules (e.g., auto-assign tickets, archive, or mark as spam). |
| `SUPPORTBEE_CREATE_EMAIL` | Create Forwarding Email | Create a new forwarding email address for the company in SupportBee. Use this to add new support email addresses that will forward incoming emails to your SupportBee account as tickets. |
| `SUPPORTBEE_CREATE_FILTER` | Create Filter | Creates a filter in SupportBee by linking a rule with a consequence. Use this after creating both a rule (defining match conditions) and a consequence (defining actions to perform). |
| `SUPPORTBEE_CREATE_RULE` | Create Rule | Creates a new automation rule in SupportBee to automatically process tickets based on conditions. Rules allow you to automate ticket workflows by: - Matching tickets based on field conditions (subject, sender, body, etc.) - Automatically applying actions like labeling, archiving, assigning, or setting priority Use this after fetching available labels/teams to get valid IDs for actions. The rule will be evaluated for all new and existing tickets matching the conditions. Returns the created rule's unique ID. |
| `SUPPORTBEE_CREATE_SNIPPET` | Create Snippet | Create a reusable snippet (canned response) in SupportBee. Snippets are pre-written text templates that agents can quickly insert into ticket replies. Use this to create standard responses for common customer inquiries like refunds, FAQs, or welcome messages. |
| `SUPPORTBEE_CREATE_TICKET` | Create SupportBee Ticket | Creates a new support ticket in SupportBee with a subject, content, and requester details. Use this action to: - Create tickets from customer inquiries or issues - Assign tickets to specific agents or teams during creation - Add tags and labels for better ticket organization - Include CC recipients to keep stakeholders informed The ticket will be created in an unanswered state and will appear in the inbox unless marked as spam. |
| `SUPPORTBEE_CREATE_TICKET_REPLY` | Create Ticket Reply | Create a reply to a support ticket in SupportBee. Replies are sent to customers via email and are visible to them. Use this when you need to respond to a customer's ticket with information, updates, or solutions. Provide the ticket ID and HTML-formatted content for your reply. |
| `SUPPORTBEE_CREATE_USER_OR_CUSTOMER_GROUP` | Create SupportBee User | Invites a new user to your SupportBee account. The user will receive an email invitation and can be assigned as an agent (handles tickets), admin (full access), or collaborator (view/comment only). Use this when you need to add team members to your helpdesk programmatically. |
| `SUPPORTBEE_DELETE_SNIPPET` | Delete Snippet | Permanently delete a snippet by its ID from SupportBee. Use this action when you need to remove an unwanted or outdated snippet (canned response template). This action is destructive and cannot be undone. To find snippet IDs, use the 'Fetch Snippets' action first. |
| `SUPPORTBEE_DELETE_TICKET` | Delete SupportBee Ticket | Permanently delete a trashed ticket from SupportBee. The ticket must first be moved to trash using the Trash Ticket action before it can be permanently deleted. Only admins can delete trashed tickets. This action is irreversible. |
| `SUPPORTBEE_FETCH_EMAILS` | Fetch Forwarding Emails | Retrieve all forwarding email addresses configured for the company. Use this tool to list the support email addresses that forward emails to SupportBee. |
| `SUPPORTBEE_FETCH_LABELS` | Fetch SupportBee Labels | Tool to retrieve all custom labels. Use when you need to list labels for ticket categorization. |
| `SUPPORTBEE_FETCH_SNIPPETS` | Fetch Snippets | Fetches saved response snippets (canned responses/templates) from SupportBee. Snippets are reusable text templates that can be inserted into ticket replies. Use this to list available snippets for quick responses. |
| `SUPPORTBEE_FETCH_TEAMS` | Fetch SupportBee Teams | Retrieves all teams in the SupportBee account. Use this to list available teams before assigning tickets to teams or filtering tickets by team. Returns team IDs, names, descriptions, and timestamps. |
| `SUPPORTBEE_GET_AVG_FIRST_RESPONSE_TIME_REPORT` | Get Avg First Response Time Report | Tool to retrieve average first response time data points over time. Use when analyzing first-response performance metrics for support tickets. Returns time-series data with response times in seconds and Unix timestamps. Reports require admin API token access. Data is limited to a maximum 30-day window per request. |
| `SUPPORTBEE_GET_REPLIES_COUNT_REPORT` | Get Replies Count Report | Retrieves replies count report data for the company. Returns time-series data points showing the number of replies over time. The report provides aggregate metrics for the entire company account and includes type information (company/user/team), the entity ID, and the metric name. Requires admin-level API access. Use this to analyze reply volume trends and patterns. |
| `SUPPORTBEE_GET_TICKET` | Get Ticket | Tool to retrieve a specific SupportBee ticket by its ID. Returns complete ticket details including subject, content, requester, assignee, labels, and reply/comment counts. Use when you need to fetch full details of a single ticket. |
| `SUPPORTBEE_GET_TICKETS_COUNT_REPORT` | Get Tickets Count Report | Tool to get ticket count data points over time. Use when analyzing ticket volume trends within a specific date range. Supports optional filtering by agent, team, or label. |
| `SUPPORTBEE_LIST_TICKET_COMMENTS` | List Ticket Comments | Retrieves all internal comments (private agent notes) for a specific ticket. Comments are visible only to agents within the helpdesk, not to customers. Use this to review internal discussion history on a ticket. |
| `SUPPORTBEE_LIST_TICKET_REPLIES` | List Ticket Replies | Lists all replies on a specific support ticket in SupportBee. Returns reply content, replier details, timestamps, and attachments. Use this to view the conversation history on a ticket. Returns an empty list if the ticket has no replies yet. |
| `SUPPORTBEE_LIST_TICKETS` | List Tickets | Tool to list tickets from SupportBee. Returns a paginated list of tickets with optional filters for spam, trash, archived, assigned user/group, labels, and more. Use when you need to retrieve and browse tickets in the helpdesk. |
| `SUPPORTBEE_LIST_USERS` | List SupportBee Users | Retrieves all users and customer groups in your SupportBee company. Use this when you need to list team members, filter by user type (agents/admins vs customer groups), or include invited users who haven't confirmed their accounts yet. |
| `SUPPORTBEE_MARK_TICKET_AS_ANSWERED` | Mark SupportBee Ticket as Answered | Marks a SupportBee ticket as answered by adding the 'answered' status. Use this after sending a response to a customer to indicate the ticket has been addressed. This action is idempotent - calling it on an already answered ticket has no adverse effect. |
| `SUPPORTBEE_MARK_TICKET_AS_SPAM` | Mark SupportBee Ticket as Spam | Tool to mark a SupportBee ticket as spam. Use when you need to flag unwanted or malicious ticket submissions after obtaining the ticket ID. |
| `SUPPORTBEE_MARK_TICKET_AS_UNANSWERED` | Mark SupportBee Ticket as Unanswered | Marks a SupportBee ticket as unanswered by removing its 'answered' status. Use this to revert a ticket's status after it was previously marked as answered, typically when additional follow-up is needed from the support team. This action is idempotent - calling it on an already unanswered ticket has no adverse effect. |
| `SUPPORTBEE_REMOVE_LABEL_FROM_TICKET` | Remove Label From Ticket | Tool to remove a label from a ticket. Use when you need to unlabel or uncategorize a ticket by removing an existing label. |
| `SUPPORTBEE_SEARCH_TICKETS` | Search SupportBee Tickets | Tool to search SupportBee tickets. Use when you need to find tickets by query with pagination. |
| `SUPPORTBEE_SHOW_TICKET_REPLY` | Show Ticket Reply | Tool to fetch a specific reply for a SupportBee ticket. Use when you need details of a single reply by ticket and reply IDs. |
| `SUPPORTBEE_SHOW_USER_OR_CUSTOMER_GROUP` | Show SupportBee User or Customer Group | Retrieves details of a SupportBee user (agent/admin) or customer group by their ID. Use this action when you need to fetch profile information like name, email, role, or timestamps for a specific user whose ID you already have (e.g., from a ticket response). |
| `SUPPORTBEE_TRASH_TICKET` | Trash SupportBee Ticket | Tool to trash a SupportBee ticket by its ID. Use when you need to remove a ticket into the trash folder. |
| `SUPPORTBEE_UNARCHIVE_TICKET` | Unarchive SupportBee Ticket | Tool to unarchive a SupportBee ticket by its ID. Use when you need to restore an archived ticket back to active status. |
| `SUPPORTBEE_UNASSIGN_TICKET_FROM_TEAM` | Unassign Ticket from Team | Tool to un-assign a ticket from its assigned team. Use when you need to remove the current team ownership before reassigning or closing the ticket. |
| `SUPPORTBEE_UNASSIGN_TICKET_FROM_USER` | Unassign User From Ticket | Tool to un-assign a ticket from its assigned user/agent. Use when you need to remove the current user ownership before reassigning to a different user or closing the ticket. |
| `SUPPORTBEE_UNMARK_TICKET_AS_SPAM` | Unmark SupportBee Ticket as Spam | Tool to unmark a SupportBee ticket as spam. Use when a ticket was incorrectly flagged as spam. |
| `SUPPORTBEE_UNTRASH_TICKET` | Untrash SupportBee Ticket | Restores a trashed SupportBee ticket back to active status. Use when you need to recover a ticket that was previously moved to trash. |
| `SUPPORTBEE_UPDATE_SNIPPET` | Update Snippet | Update an existing snippet (canned response) in SupportBee. Use this to modify the name, content, or tags of a snippet. To find snippet IDs, use the 'Fetch Snippets' action first. |
| `SUPPORTBEE_UPDATE_USER` | Update SupportBee User | Update an existing SupportBee user's profile information including name, email, role, avatar, or signature. This action modifies user account details via the SupportBee API. You can update one or multiple fields in a single request. Commonly used to change user roles (agent/admin), update contact information, or customize user profiles. Requirements: - Valid user ID (obtain from SUPPORTBEE_CREATE_USER_OR_CUSTOMER_GROUP or other user-related actions) - At least one field to update (name, email, role, avatar_url, or signature) Common use cases: - Promote an agent to admin by updating the role field - Update user email addresses when they change - Customize user signatures for support ticket replies |

## Supported Triggers

None listed.

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

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

mcp_url = session.mcp.url
```

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

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

## Related Toolkits

- [Aeroleads](https://composio.dev/toolkits/aeroleads) - Aeroleads is a B2B lead generation platform for finding business emails and phone numbers. Grow your sales pipeline faster with powerful prospecting tools.
- [Autobound](https://composio.dev/toolkits/autobound) - Autobound is an AI-powered sales engagement platform that crafts hyper-personalized outreach and insights. It helps sales teams boost response rates and close more deals through tailored content and recommendations.
- [Better proposals](https://composio.dev/toolkits/better_proposals) - Better Proposals is a web-based tool for crafting and sending professional proposals. It helps teams impress clients and close deals faster with slick, easy-to-use templates.
- [Bidsketch](https://composio.dev/toolkits/bidsketch) - Bidsketch is a proposal software that helps businesses create professional proposals quickly and efficiently. It streamlines the proposal process, saving time while boosting client win rates.
- [Bolna](https://composio.dev/toolkits/bolna) - Bolna is an AI platform for building conversational voice agents. It helps businesses automate support and streamline interactions through natural, voice-powered conversations.
- [Botsonic](https://composio.dev/toolkits/botsonic) - Botsonic is a no-code AI chatbot builder for easily creating and deploying chatbots to your website. It empowers businesses to offer conversational experiences without writing code.
- [Botstar](https://composio.dev/toolkits/botstar) - BotStar is a comprehensive chatbot platform for designing, developing, and training chatbots visually on Messenger and websites. It helps businesses automate conversations and customer interactions without coding.
- [Callerapi](https://composio.dev/toolkits/callerapi) - CallerAPI is a white-label caller identification platform for branded caller ID and fraud prevention. It helps businesses boost customer trust while stopping spam, fraud, and robocalls.
- [Callingly](https://composio.dev/toolkits/callingly) - Callingly is a lead response management platform that automates immediate call and text follow-ups with new leads. It helps sales teams boost response speed and close more deals by connecting seamlessly with CRMs and lead sources.
- [Callpage](https://composio.dev/toolkits/callpage) - Callpage is a lead capture platform that lets businesses instantly connect with website visitors via callback. It boosts lead generation and increases your sales conversion rates.
- [Clearout](https://composio.dev/toolkits/clearout) - Clearout is an AI-powered service for verifying, finding, and enriching email addresses. It boosts deliverability and helps you discover high-quality leads effortlessly.
- [Clientary](https://composio.dev/toolkits/clientary) - Clientary is a platform for managing clients, invoices, projects, proposals, and more. It streamlines client work and saves you serious admin time.
- [Convolo ai](https://composio.dev/toolkits/convolo_ai) - Convolo ai is an AI-powered communications platform for sales teams. It accelerates lead response and improves conversion rates by automating calls and integrating workflows.
- [Delighted](https://composio.dev/toolkits/delighted) - Delighted is a customer feedback platform based on the Net Promoter System®. It helps you quickly gather, track, and act on customer sentiment.
- [Emelia](https://composio.dev/toolkits/emelia) - Emelia is an all-in-one B2B prospecting platform for cold-email, LinkedIn outreach, and prospect research. It streamlines outbound campaigns so you can find, engage, and warm up leads faster.
- [Findymail](https://composio.dev/toolkits/findymail) - Findymail is a B2B data provider offering verified email and phone contacts for sales prospecting. Enhance outreach with automated exports, email verification, and CRM enrichment.
- [Freshdesk](https://composio.dev/toolkits/freshdesk) - Freshdesk is customer support software with ticketing and automation tools. It helps teams streamline helpdesk operations for faster, better customer support.
- [Fullenrich](https://composio.dev/toolkits/fullenrich) - FullEnrich is a B2B contact enrichment platform that aggregates emails and phone numbers from 15+ data vendors. Instantly find and verify lead contact data to boost your outreach.
- [Gatherup](https://composio.dev/toolkits/gatherup) - GatherUp is a customer feedback and online review management platform. It helps businesses boost their reputation by streamlining how they collect and manage customer feedback.
- [Getprospect](https://composio.dev/toolkits/getprospect) - Getprospect is a business email discovery tool with LinkedIn integration. Use it to quickly find and verify professional email addresses.

## Frequently Asked Questions

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

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

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

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

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