How to integrate FuseDesk MCP with Autogen

This guide walks you through connecting FuseDesk to AutoGen using the Composio tool router. By the end, you'll have a working FuseDesk agent that can create support cases, view case details, add case notes, tag cases, and merge duplicate cases through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a FuseDesk account through Composio's FuseDesk MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
FuseDesk logoFuseDesk
Api Key

FuseDesk is a customer support platform for managing cases, email conversations, contacts, departments, representatives, chats, and webhooks. It helps support teams keep customer conversations organized so issues get routed, tracked, and resolved faster.

27 Tools

Introduction

This guide walks you through connecting FuseDesk to AutoGen using the Composio tool router. By the end, you'll have a working FuseDesk agent that can create support cases, view case details, add case notes, tag cases, and merge duplicate cases through natural language commands.

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

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

Also integrate FuseDesk with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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

The FuseDesk MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your FuseDesk account. It provides structured and secure access to support cases, email conversations, contacts, departments, representatives, chats, and webhooks, so your agent can create and update cases, reply to customers, manage contacts, monitor chats, and review support activity on your behalf.

  • Case creation and management: Have your agent open support cases, update their content or status, change tags, add internal notes, snooze follow-ups, and merge related cases.
  • Customer replies and email review: Let the agent search support emails, read complete messages, and send replies to customers from the appropriate case.
  • Contact and team coordination: Direct your agent to create, find, and update contacts, review departments, and check representative profiles when deciding where work belongs.
  • Chat monitoring and handling: Instruct your agent to list active chats, read conversation histories, transfer or rename chats, mark them seen or unseen, and close completed conversations.
  • Support oversight and automation review: Have your agent search cases by customer, assignment, status, text, or date, apply bulk changes, review case tags, and list configured webhook subscriptions.

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 FuseDesk 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 FuseDesk 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 FuseDesk 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 FuseDesk session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["fusedesk"]
    )
    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 FuseDesk 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 FuseDesk assistant agent with MCP tools
    agent = AssistantAgent(
        name="fusedesk_assistant",
        description="An AI assistant that helps with FuseDesk 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 FuseDesk 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 FuseDesk 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 FuseDesk 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 FuseDesk 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 FuseDesk session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["fusedesk"]
    )
    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 FuseDesk assistant agent with MCP tools
        agent = AssistantAgent(
            name="fusedesk_assistant",
            description="An AI assistant that helps with FuseDesk 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 FuseDesk 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 FuseDesk 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 FuseDesk, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

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

Add Case Note

Add an internal note or call record to a case and optionally change its status.

Bulk Merge Cases

Irreversibly merge multiple FuseDesk cases.

Bulk Update Cases

Apply an assignment, department, status, tag, CRM automation, CRM tag, or snooze operation to multiple FuseDesk cases.

Change Case Tag

Apply or remove one existing case tag from one FuseDesk case.

Close Chat

Irreversibly close a FuseDesk chat and end the live conversation.

Create Case

Open a support case for a customer in a FuseDesk department.

Create Case Tag

Create a reusable FuseDesk case tag.

Create Contact

Create a FuseDesk contact.

Get Case

Get one FuseDesk support case and its complete history by case ID.

Get Chat

Get one FuseDesk chat and its complete message history by chat UUID.

Get Contact

Get a FuseDesk contact by UUID, including current data from its linked CRM contact.

Get Department

Get a FuseDesk department's assignment, template, staleness, feedback, phone, and archive settings by department ID.

Get Email

Get one FuseDesk email by its numeric ID, including its complete body.

Get Rep

Get a FuseDesk rep's detailed profile, permissions, and signatures.

List Case Tags

List available FuseDesk case tags and their case counts.

List Chats

List active FuseDesk chats across connected chat platforms, including assignment links, recent-message context, and lifecycle state.

List Departments

List active, archived, or all FuseDesk departments using the current v2 representation.

List Reps

List active and disabled FuseDesk reps for assignment and ownership decisions.

List Webhooks

List configured FuseDesk webhook subscriptions.

Reply To Case

Send an external email reply on a FuseDesk case using supplied content or an existing reply template.

Search Cases

Search support cases by customer, assignment, status, text, and lifecycle dates, returning one controllable page.

Search Contacts

Search FuseDesk and linked CRM contacts by required text.

Search Emails

Search all or only unassigned FuseDesk emails, returning one controllable page with optionally truncated bodies.

Snooze Case

Snooze a case until an absolute date/time or FuseDesk relative-time expression.

Update Case

Change a case's content, customer link, assignment, department, or status.

Update Chat

Rename, transfer, relink, or mark a live FuseDesk chat seen or unseen.

Update Contact

Update a FuseDesk contact.

FRAMEWORKS

How to build FuseDesk MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use FuseDesk MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use FuseDesk MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use FuseDesk MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use FuseDesk MCP with Claude Cowork

Codex logo

Codex

Use FuseDesk MCP with Codex

OpenClaw logo

OpenClaw

Use FuseDesk MCP with OpenClaw

Hermes logo

Hermes

Use FuseDesk MCP with Hermes

CLI logo

CLI

Use FuseDesk MCP with CLI

Google ADK logo

Google ADK

Use FuseDesk MCP with Google ADK

LangChain logo

LangChain

Use FuseDesk MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use FuseDesk MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use FuseDesk MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use FuseDesk MCP with LlamaIndex

CrewAI logo

CrewAI

Use FuseDesk MCP with CrewAI

FAQ

Frequently asked questions

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

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 FuseDesk tools.

Yes, absolutely. You can configure which FuseDesk 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.

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 FuseDesk data and credentials are handled as safely as possible.

Start with FuseDesk.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies