How to integrate Chatbotkit MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Chatbotkit Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Chatbotkit to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Chatbotkit agent that can list all bots i’ve deployed, show recent messages in a conversation, create a new skillset for support, list all integrations for my chatbot through natural language commands.

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

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

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 Chatbotkit
  • Configure an AI agent that can use Chatbotkit as a tool
  • Run a live chat session where you can ask the agent to perform Chatbotkit operations

What is open-ai-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 Chatbotkit MCP server, and what's possible with it?

The Chatbotkit MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Chatbotkit account. It provides structured and secure access to your chatbot platform, so your agent can perform actions like managing bots, handling conversations, integrating support channels, and organizing skillsets on your behalf.

  • Manage and list bots: Effortlessly retrieve and manage all of your chatbots, making it simple to keep tabs on each one in your workspace.
  • Conversation tracking and messaging: Browse conversation history, fetch conversation messages, and send new messages for dynamic real-time interactions with users.
  • Integration setup and management: Create and list integrations to connect your bots with external channels or support systems without manual configuration.
  • Skillset and dataset organization: Create, list, and manage skillsets and datasets to extend your bots’ capabilities and tailor responses to your business needs.
  • Partner and sub-account management: View and organize all partner accounts or sub-accounts associated with your main Chatbotkit account for streamlined administration.

Supported Tools & Triggers

Tools
Complete ConversationTool to send a message to a conversation and receive the bot’s reply.
Create IntegrationTool to create a new integration.
Create SkillsetTool to create a new skillset.
List BotsTool to retrieve a paginated list of all bots.
List conversation messagesTool to list messages in a conversation with pagination.
List ConversationsTool to retrieve a paginated list of conversations.
List DatasetsTool to list datasets.
List IntegrationsTool to retrieve a list of trigger integrations.
List PartnersTool to retrieve a list of all partner accounts associated with the main account.
List SkillsetsTool to retrieve a list of all skillsets available in the system.
List TokensTool to retrieve a list of all api tokens.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

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

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

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
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 Chatbotkit.

Set up the Composio instance

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())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Chatbotkit Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["chatbotkit"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only chatbotkit.
  • The router checks the user's Chatbotkit connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Chatbotkit.
  • This approach keeps things lightweight and lets the agent request Chatbotkit tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Chatbotkit. "
        "Help users perform Chatbotkit 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",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Chatbotkit and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Chatbotkit operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

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())
What's happening:
  • The program prints a session URL that you visit to authorize Chatbotkit.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Chatbotkit and open-ai-agents-sdk:

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=["chatbotkit"]
)
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 Chatbotkit. "
        "Help users perform Chatbotkit 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())

Conclusion

This was a starter code for integrating Chatbotkit MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Chatbotkit.

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 Chatbotkit MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Chatbotkit MCP with Claude Agent SDK

Google ADK

Google ADK

Use Chatbotkit MCP with Google ADK

LangChain

LangChain

Use Chatbotkit MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Chatbotkit MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Chatbotkit MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Chatbotkit MCP with LlamaIndex

CrewAI

CrewAI

Use Chatbotkit MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Chatbotkit MCP?

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

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

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

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free