SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Helpdesk MCP with Autogen

Connect Autogen to Helpdesk MCP. List all agents available for support, show all active canned responses for tickets, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Helpdesk logoHelpdesk
Api Key

HelpDesk is a ticketing platform that organizes and manages customer support inquiries. It helps teams streamline their support workflows and respond to customers efficiently.

14 Tools

Introduction

This guide walks you through connecting Helpdesk to AutoGen using the Composio tool router. By the end, you'll have a working Helpdesk agent that can list tickets and views, browse agents and teams, review canned responses and rules, and check custom fields through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Helpdesk account through Composio's Helpdesk MCP server.

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Helpdesk with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

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 Helpdesk
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Helpdesk tools
  • Run a live chat loop where you ask the agent to perform Helpdesk 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 Helpdesk MCP server, and what's possible with it?

The Helpdesk MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Helpdesk account. It provides structured and secure access to your ticketing system, so your agent can perform actions like listing support agents, managing contacts, retrieving canned responses, and reviewing automation rules on your behalf.

  • Agent and team management: Instantly list all support agents and teams in your Helpdesk account, making it easy to organize and delegate customer inquiries.
  • Contact and subscription retrieval: Pull up detailed contact lists and subscription information so your agent always has up-to-date customer and account data at hand.
  • Canned response access: Let your agent fetch and suggest predefined reply templates, ensuring fast and consistent communication with customers.
  • Rules and automation overview: Review all configured automation rules in your helpdesk, helping your agent stay aligned with your business processes and ticketing workflows.
  • Account configuration insights: Retrieve lists of custom fields, reply addresses, licenses, and email domains to support personalized automation and account management tasks.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Helpdesk account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

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.
3

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 Helpdesk via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

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 Helpdesk connections to use
5

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 Helpdesk session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["helpdesk"]
    )
    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 Helpdesk tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

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
7

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 Helpdesk assistant agent with MCP tools
    agent = AssistantAgent(
        name="helpdesk_assistant",
        description="An AI assistant that helps with Helpdesk 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 Helpdesk tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Helpdesk 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 Helpdesk 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 Helpdesk 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 Helpdesk session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["helpdesk"]
    )
    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 Helpdesk assistant agent with MCP tools
        agent = AssistantAgent(
            name="helpdesk_assistant",
            description="An AI assistant that helps with Helpdesk 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 Helpdesk 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 Helpdesk 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 Helpdesk, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Helpdesk action and event your agent gets out of the box.

List Agents

Lists support agents in the HelpDesk account, including their profiles, roles, team memberships, status, auto-assignment settings, and signatures.

List Canned Responses

Tool to list canned responses.

List Custom Fields

Tool to list all custom fields defined in the account.

List Email Domains

Lists all email domains configured for the HelpDesk account.

List Licenses

Retrieves all licenses (account configurations) for the authenticated HelpDesk account.

List Reply Addresses

Lists all reply addresses configured in the HelpDesk account.

List Rules

Tool to retrieve a list of rules configured in the account.

List Subscriptions

Lists all billing subscriptions for the HelpDesk account, including active, expired, canceled, and future subscriptions.

List Teams

Lists all teams in the HelpDesk account.

List Tickets

Lists tickets from a specified silo using cursor-based pagination, configurable page size, and sorting.

List Trusted Emails

Tool to retrieve a list of trusted email addresses or domains.

List Views

Tool to list agent views.

List Webhooks

Lists configured HelpDesk webhooks for ticket events.

View Agent

Retrieves comprehensive details for a specific agent in the HelpDesk system.

FRAMEWORKS

How to build Helpdesk MCP Agent with another framework

Claude Code logo

Claude Code

Use Helpdesk MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Helpdesk MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Helpdesk MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Helpdesk MCP with Claude Agent SDK

Codex logo

Codex

Use Helpdesk MCP with Codex

OpenClaw logo

OpenClaw

Use Helpdesk MCP with OpenClaw

Hermes logo

Hermes

Use Helpdesk MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Helpdesk MCP with Atomic Agent

Google ADK logo

Google ADK

Use Helpdesk MCP with Google ADK

LangChain logo

LangChain

Use Helpdesk MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Helpdesk MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Helpdesk MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Helpdesk MCP with LlamaIndex

CrewAI logo

CrewAI

Use Helpdesk MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Helpdesk MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Helpdesk.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Helpdesk tool your agent needs.Free to start.

Start building