# How to integrate Zoho desk MCP with Autogen ```json { "title": "How to integrate Zoho desk MCP with Autogen", "toolkit": "Zoho desk", "toolkit_slug": "zoho_desk", "framework": "AutoGen", "framework_slug": "autogen", "url": "https://composio.dev/toolkits/zoho_desk/framework/autogen", "markdown_url": "https://composio.dev/toolkits/zoho_desk/framework/autogen.md", "updated_at": "2026-10-12T13:32:28.984Z" } ``` ## Introduction This guide walks you through connecting Zoho desk to AutoGen using the Composio tool router. By the end, you'll have a working Zoho desk agent that can list high-priority open support tickets, summarize recent customer interactions today, create new ticket for incoming email through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Zoho desk account through Composio's Zoho desk MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Zoho desk with - [Claude Code](https://composio.dev/toolkits/zoho_desk/framework/claude-code) - [Cursor](https://composio.dev/toolkits/zoho_desk/framework/cursor) - [ChatGPT](https://composio.dev/toolkits/zoho_desk/framework/chatgpt) - [Claude Cowork](https://composio.dev/toolkits/zoho_desk/framework/claude-cowork) - [Antigravity](https://composio.dev/toolkits/zoho_desk/framework/antigravity) - [OpenAI Agents SDK](https://composio.dev/toolkits/zoho_desk/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/zoho_desk/framework/claude-agents-sdk) - [Codex](https://composio.dev/toolkits/zoho_desk/framework/codex) - [Grok Build](https://composio.dev/toolkits/zoho_desk/framework/grok-build) - [VS Code](https://composio.dev/toolkits/zoho_desk/framework/vscode) - [OpenCode](https://composio.dev/toolkits/zoho_desk/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/zoho_desk/framework/openclaw) - [Hermes](https://composio.dev/toolkits/zoho_desk/framework/hermes-agent) - [Atomic Agent](https://composio.dev/toolkits/zoho_desk/framework/atomic-agent) - [Google ADK](https://composio.dev/toolkits/zoho_desk/framework/google-adk) - [LangChain](https://composio.dev/toolkits/zoho_desk/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/zoho_desk/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/zoho_desk/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/zoho_desk/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/zoho_desk/framework/crew-ai) - [Pydantic AI](https://composio.dev/toolkits/zoho_desk/framework/pydantic-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 Zoho desk - Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams - Configure an Autogen AssistantAgent that can call Zoho desk tools - Run a live chat loop where you ask the agent to perform Zoho desk 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 Zoho desk MCP server, and what's possible with it? The Zoho desk MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Zoho Desk account. It provides structured and secure access to your helpdesk workspace, so your agent can perform actions like tracking support tickets, managing customer conversations, automating ticket workflows, and generating support insights on your behalf. - Ticket tracking and management: Let your agent create, update, and monitor support tickets, ensuring customer inquiries are handled efficiently. - Automated workflow execution: Empower your agent to automate repetitive support processes, such as assigning tickets or escalating issues based on rules. - Customer communication handling: Enable your agent to fetch and organize customer conversations, keeping your team informed and responsive. - Insightful analytics and reporting: Have your agent generate detailed reports and metrics on ticket trends, response times, and agent performance for better decision-making. - Collaboration with support teams: Allow your agent to coordinate with team members by tagging, commenting, or sharing ticket information securely within Zoho Desk. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `ZOHO_DESK_CREATE_CONTACT` | Create Contact | Tool to create a new contact in Zoho Desk with name, email, and other details. Use this action when you need to add a new contact to the system, such as when onboarding a new customer or registering a support requester. Returns the created contact with id and webUrl for downstream operations. | | `ZOHO_DESK_CREATE_TICKET` | Create Ticket | Tool to create a new Zoho Desk ticket with subject, description, department, and requester details. Use when you need to create a support ticket in Zoho Desk. Returns the created ticket with id and webUrl for downstream chaining. | | `ZOHO_DESK_DOWNLOAD_TICKET_ATTACHMENT` | Download Ticket Attachment | Download a file attachment from a Zoho Desk ticket by attachment ID. Use this action when you need to retrieve a specific file that was previously attached to a ticket. Requires both the ticket ID and the attachment ID to identify the file to download. | | `ZOHO_DESK_GET_AGENT` | Get Agent | Tool to fetch details of a Zoho Desk agent. Use when you have an agent ID and need its full data, optionally including related resources. | | `ZOHO_DESK_GET_AGENTS_COUNT` | Get Agents Count | Tool to get the total count of agents in Zoho Desk. Use when you need the number of agents optionally filtered by status, confirmation, or light agents. | | `ZOHO_DESK_GET_CONTACT` | Get Contact | Tool to fetch details of a Zoho Desk contact. Use when you have a contact ID and need its full data, optionally including accounts or owner details. | | `ZOHO_DESK_GET_CONTACTS_BY_IDS` | Get Contacts By IDs | Tool to fetch multiple contacts by their IDs using Zoho Desk's contactsByIds endpoint. | | `ZOHO_DESK_GET_DEPARTMENT` | Get Department | Tool to fetch details of a Zoho Desk department by ID. | | `ZOHO_DESK_GET_DEPARTMENT_LOGO` | Get Department Logo | Tool to get/download a department's logo from Zoho Desk. | | `ZOHO_DESK_GET_DEPARTMENTS_COUNT` | Get Departments Count | Tool to get the total count of departments in Zoho Desk. Use when you need the number of departments, optionally filtered by enabled status. | | `ZOHO_DESK_GET_TICKET` | Get Ticket | Get Ticket | | `ZOHO_DESK_GET_TICKET_LATEST_THREAD` | Get Ticket Latest Thread | Tool to fetch the most recent thread of a ticket. Use when you need the latest conversation on a ticket. | | `ZOHO_DESK_GET_TICKET_RESOLUTION` | Get Ticket Resolution | Get Ticket Resolution | | `ZOHO_DESK_GET_TICKET_THREAD` | Get Ticket Thread | Tool to fetch a specific thread within a Zoho Desk ticket. Use when you need detailed thread information by ticket and thread IDs. | | `ZOHO_DESK_LIST_AGENTS` | List Agents | Tool to list all agents in the Zoho Desk organization with optional filtering and pagination. Use when you need to retrieve multiple agents, optionally filtered by status or confirmation state. | | `ZOHO_DESK_LIST_CONTACT_ACCOUNTS` | List Contact Accounts | Tool to list accounts associated with a Zoho Desk contact. Use when you need to retrieve the accounts linked to a specific contact. | | `ZOHO_DESK_LIST_CONTACTS` | List Contacts | Tool to list contacts with filters and pagination. Use when you need to fetch contacts from Zoho Desk with optional filtering, sorting, or field selection. | | `ZOHO_DESK_LIST_DEPARTMENTS` | List Departments | Tool to list all departments in the current Zoho Desk organization. | | `ZOHO_DESK_LIST_ORGANIZATIONS` | List Organizations | Tool to list all organizations the current user belongs to. Use when you need to retrieve organization metadata like portal URLs, names, and editions. | | `ZOHO_DESK_LIST_ROLES` | List Roles | List Roles | | `ZOHO_DESK_LIST_ROLES_BY_IDS` | List Roles By IDs | List Roles By IDs | | `ZOHO_DESK_LIST_TEAMS_IN_DEPARTMENT` | List Teams in Department | Tool to list teams in the specified Zoho Desk department. | | `ZOHO_DESK_LIST_TICKET_CONVERSATIONS` | List Ticket Conversations | List Ticket Conversations | | `ZOHO_DESK_LIST_TICKET_HISTORY` | List Ticket History | List audit and activity history for a ticket. History records describe ticket changes and actions. Use the conversation or thread actions instead when you need message and comment content. | | `ZOHO_DESK_LIST_TICKETS` | List Tickets | List Tickets | | `ZOHO_DESK_LIST_TICKET_THREADS` | List Ticket Threads | List message threads recorded on a Zoho Desk ticket. This returns threads only. Use the conversations action when comments and threads should be returned together. | | `ZOHO_DESK_LIST_VIEWS` | List Views | List all ticket views in the Zoho Desk organization with pagination support. Views are saved filters that help organize and display tickets based on specific criteria. Use this action when you need to retrieve available views for filtering tickets, such as before calling the list tickets endpoint with a specific viewId. | | `ZOHO_DESK_SEARCH` | Search | Search across Zoho Desk modules including tickets, accounts, contacts, and tasks using keywords or phrases. Use this action when you need to find records across multiple modules or within a specific module based on search criteria. Returns matching results with pagination support. | | `ZOHO_DESK_UPDATE_ACCOUNT` | Update Account | Tool to update an existing Zoho Desk account's information such as name, email, phone, website, or description. Use this action when you need to modify account details after the account has been created. Only the fields you provide will be updated; other fields remain unchanged. | | `ZOHO_DESK_UPDATE_MANY_TASKS` | Update Many Tasks | Update multiple tasks in a single call using Zoho Desk API. Endpoint: POST /api/v1/tasks/updateMany | | `ZOHO_DESK_UPDATE_TICKET` | Update Ticket | Updates an existing Zoho Desk ticket by modifying one or more fields such as status, priority, assignee, description, or other ticket properties. Use this action when you need to modify an existing support ticket in Zoho Desk, such as changing its status, reassigning it to a different agent, updating priority, or adding information. Returns the updated ticket object with all current field values including the modified fields. | | `ZOHO_DESK_UPLOAD_DEPARTMENT_LOGO` | Upload Department Logo | Tool to upload/update a department logo in Zoho Desk. | | `ZOHO_DESK_UPLOAD_TICKET_ATTACHMENT` | Upload Ticket Attachment | Uploads a file attachment to a specific Zoho Desk ticket. The uploaded file becomes accessible as an attachment within the ticket for support agents and customers to reference. Use this action when you need to attach documentation, screenshots, logs, or any supporting files to an existing ticket. Maximum file size is 20 MB per attachment. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Zoho desk MCP server is an implementation of the Model Context Protocol that connects your AI agents and assistants directly to Zoho desk. Instead of manually wiring Zoho desk APIs, OAuth, and scopes yourself, you get a structured, tool-based interface that an LLM can call safely. 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 You will need: - A Composio API key - An OpenAI API key (used by Autogen's OpenAIChatCompletionClient) - A Zoho desk account you can connect to Composio - Some basic familiarity with Autogen and Python async ### 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). - Navigate to your API settings and generate a new API key. - Store this key securely as you'll need it for authentication. ### 2. Install dependencies Install Composio, Autogen extensions, and dotenv. What's happening: - composio connects your agent to Zoho desk via MCP - autogen-agentchat provides the AssistantAgent class - autogen-ext-openai provides the OpenAI model client - autogen-ext-tools provides MCP workbench support ```bash pip install composio python-dotenv pip install autogen-agentchat autogen-ext-openai autogen-ext-tools ``` ### 3. Set up environment variables 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 Zoho desk connections to use ```bash COMPOSIO_API_KEY=your-composio-api-key OPENAI_API_KEY=your-openai-api-key USER_ID=your-user-identifier@example.com ``` ### 4. Import dependencies and create Tool Router session What's happening: - load_dotenv() reads your .env file - Composio(api_key=...) initializes the SDK - create(...) creates a Tool Router session that exposes Zoho desk tools - session.mcp.url is the MCP endpoint that Autogen will connect to ```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 Zoho desk session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["zoho_desk"] ) url = session.mcp.url ``` ### 5. Configure MCP parameters for Autogen 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 ```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")} ) ``` ### 6. Create the model client and agent What's happening: - OpenAIChatCompletionClient wraps the OpenAI model for Autogen - McpWorkbench connects the agent to the MCP tools - AssistantAgent is configured with the Zoho desk tools from the workbench ```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 Zoho desk assistant agent with MCP tools agent = AssistantAgent( name="zoho_desk_assistant", description="An AI assistant that helps with Zoho desk operations.", model_client=model_client, workbench=workbench, model_client_stream=True, max_tool_iterations=10 ) ``` ### 7. Run the interactive chat loop What's happening: - The script prompts you in a loop with You: - Autogen passes your input to the model, which decides which Zoho desk 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 ```python print("Chat started! Type 'exit' or 'quit' to end the conversation.\n") print("Ask any Zoho desk 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") ``` ## Complete Code ```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 Zoho desk session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["zoho_desk"] ) 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 Zoho desk assistant agent with MCP tools agent = AssistantAgent( name="zoho_desk_assistant", description="An AI assistant that helps with Zoho desk 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 Zoho desk 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 Zoho desk 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 Zoho desk, you can reuse the same structure for other MCP-enabled apps with minimal code changes. ## How to build Zoho desk MCP Agent with another framework - [Claude Code](https://composio.dev/toolkits/zoho_desk/framework/claude-code) - [Cursor](https://composio.dev/toolkits/zoho_desk/framework/cursor) - [ChatGPT](https://composio.dev/toolkits/zoho_desk/framework/chatgpt) - [Claude Cowork](https://composio.dev/toolkits/zoho_desk/framework/claude-cowork) - [Antigravity](https://composio.dev/toolkits/zoho_desk/framework/antigravity) - [OpenAI Agents SDK](https://composio.dev/toolkits/zoho_desk/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/zoho_desk/framework/claude-agents-sdk) - [Codex](https://composio.dev/toolkits/zoho_desk/framework/codex) - [Grok Build](https://composio.dev/toolkits/zoho_desk/framework/grok-build) - [VS Code](https://composio.dev/toolkits/zoho_desk/framework/vscode) - [OpenCode](https://composio.dev/toolkits/zoho_desk/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/zoho_desk/framework/openclaw) - [Hermes](https://composio.dev/toolkits/zoho_desk/framework/hermes-agent) - [Atomic Agent](https://composio.dev/toolkits/zoho_desk/framework/atomic-agent) - [Google ADK](https://composio.dev/toolkits/zoho_desk/framework/google-adk) - [LangChain](https://composio.dev/toolkits/zoho_desk/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/zoho_desk/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/zoho_desk/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/zoho_desk/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/zoho_desk/framework/crew-ai) - [Pydantic AI](https://composio.dev/toolkits/zoho_desk/framework/pydantic-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. - [Botdog](https://composio.dev/toolkits/botdog) - Botdog is a LinkedIn outreach platform for managing campaigns, leads, messages, analytics, and sending accounts. It helps sales teams run outbound workflows and track performance from one place. - [BotPenguin](https://composio.dev/toolkits/botpenguin) - BotPenguin is an AI chatbot platform for customer messaging, contacts, and conversations. It helps teams manage bot-led support and lead engagement across channels. - [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. - [Charla](https://composio.dev/toolkits/charla) - Charla is a live chat and AI customer-support platform for property teams. It helps manage guest conversations, property contacts, and support knowledge. - [Chatforma](https://composio.dev/toolkits/chatforma) - Chatforma is a chatbot automation platform for building and managing bots. It helps teams run dialogs, segments, broadcasts, forms, and user updates from one place. - [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. - [Crisp](https://composio.dev/toolkits/crisp) - Crisp is a customer messaging platform for live chat, contacts, helpdesk, and campaigns. It helps support teams manage customer conversations from one shared workspace. - [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. - [Docsbot ai](https://composio.dev/toolkits/docsbot_ai) - Docsbot ai is a platform that lets you build custom AI chatbots trained on your documentation. It automates customer support and content generation, saving time and improving response quality. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Zoho desk MCP? With a standalone Zoho desk MCP server, the agents and LLMs can only access a fixed set of Zoho desk tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Zoho desk 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 Zoho desk tools. ### Can I manage the permissions and scopes for Zoho desk while using Tool Router? Yes, absolutely. You can configure which Zoho desk 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 Zoho desk data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)