How to integrate Helpwise MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Helpwise Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Helpwise to AutoGen using the Composio tool router. By the end, you'll have a working Helpwise agent that can add note to open conversation with client, delete outdated contact from contact list, create new team for support agents, upload invoice attachment to active conversation through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Helpwise account through Composio's Helpwise 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 required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Helpwise
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Helpwise tools
  • Run a live chat loop where you ask the agent to perform Helpwise operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Helpwise MCP server, and what's possible with it?

The Helpwise MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Helpwise account. It provides structured and secure access to your customer communication tools, so your agent can create conversations, manage notes, upload attachments, delete messages, and organize your Helpwise workspace on your behalf.

  • Attachment management and uploads: Easily upload files as attachments to conversations and retrieve attachment metadata for streamlined file sharing.
  • Conversation note automation: Let your agent add or remove notes to specific conversations, making it easy to document context or follow up actions.
  • Mailbox and conversation cleanup: Direct your agent to delete entire conversations, mailboxes, or individual messages for efficient workspace management.
  • Contact and signature management: Seamlessly delete contacts and email signatures, keeping your Helpwise account up to date and clutter-free.
  • Webhook and team setup: Have your agent create new webhooks for event notifications or set up Helpwise teams to organize your users for better collaboration.

Supported Tools & Triggers

Tools
Create attachmentTool to upload a new attachment.
Add note to conversationTool to add a note to a conversation.
Create Helpwise TeamTool to create a new team.
Create Helpwise WebhookTool to create a new webhook in Helpwise.
Delete ContactTool to delete a contact.
Delete Helpwise ConversationTool to delete a conversation.
Delete MailboxTool to delete a mailbox.
Delete Helpwise MessageTool to delete a message.
Delete Helpwise NoteTool to delete a note from a conversation.
Delete SignatureTool to delete an email signature.
Delete TagTool to delete a tag.
Delete TeamTool to delete a team.
Delete TemplateTool to delete a template.
Delete Helpwise WebhookTool to delete a webhook.
Get AttachmentTool to retrieve a specific attachment.
Get Conversation AttachmentsTool to retrieve attachments.
Get Helpwise ContactTool to retrieve details of a specific contact.
Get ConversationTool to retrieve details of a specific conversation.
Get ConversationsTool to retrieve a list of conversations.
Get Helpwise MailboxTool to retrieve details of a specific mailbox by its ID.
Get Helpwise MailboxesTool to retrieve mailboxes.
Get Helpwise MessagesTool to retrieve messages for a specific conversation.
Get Conversation NoteTool to retrieve details of a specific note.
Get Conversation NotesTool to retrieve notes for a conversation.
Get Helpwise TagTool to retrieve a specific tag.
Get Helpwise TeamTool to retrieve details of a specific team by its ID.
Get Helpwise TeamsTool to retrieve Helpwise teams.
Get Helpwise TemplatesTool to retrieve Helpwise email templates.
Get Helpwise UsersTool to retrieve Helpwise users list.
Get Helpwise WebhookTool to retrieve details of a specific webhook.
Get Helpwise WebhooksTool to retrieve Helpwise webhooks.
Update Helpwise ContactTool to update an existing Helpwise contact.
Update MailboxTool to update an existing mailbox.
Update Helpwise MessageTool to update an existing message.
Update Helpwise TagTool to update an existing tag.
Update Helpwise TemplateTool to update an existing email template.

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

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Helpwise account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

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
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Helpwise via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Helpwise connections to use

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Helpwise session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["helpwise"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Helpwise tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Helpwise assistant agent with MCP tools
    agent = AssistantAgent(
        name="helpwise_assistant",
        description="An AI assistant that helps with Helpwise operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Helpwise tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Helpwise related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Helpwise tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Helpwise and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Helpwise session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["helpwise"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Helpwise assistant agent with MCP tools
        agent = AssistantAgent(
            name="helpwise_assistant",
            description="An AI assistant that helps with Helpwise operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Helpwise related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Helpwise through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Helpwise, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Helpwise MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Helpwise MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Helpwise MCP with Claude Agent SDK

Google ADK

Google ADK

Use Helpwise MCP with Google ADK

LangChain

LangChain

Use Helpwise MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Helpwise MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Helpwise MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Helpwise MCP with LlamaIndex

CrewAI

CrewAI

Use Helpwise MCP with CrewAI

FAQ

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

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

Can I use Tool Router MCP with Autogen?

Yes, you can. Autogen 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 Helpwise tools.

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

Yes, absolutely. You can configure which Helpwise 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 Helpwise 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