# How to integrate Delighted MCP with Autogen ```json { "title": "How to integrate Delighted MCP with Autogen", "toolkit": "Delighted", "toolkit_slug": "delighted", "framework": "AutoGen", "framework_slug": "autogen", "url": "https://composio.dev/toolkits/delighted/framework/autogen", "markdown_url": "https://composio.dev/toolkits/delighted/framework/autogen.md", "updated_at": "2026-03-29T06:30:02.001Z" } ``` ## Introduction This guide walks you through connecting Delighted to AutoGen using the Composio tool router. By the end, you'll have a working Delighted agent that can send an nps survey to a customer, show all recent delighted feedback comments, get nps score for last quarter through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Delighted account through Composio's Delighted MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Delighted with - [OpenAI Agents SDK](https://composio.dev/toolkits/delighted/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/delighted/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/delighted/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/delighted/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/delighted/framework/codex) - [OpenClaw](https://composio.dev/toolkits/delighted/framework/openclaw) - [Hermes](https://composio.dev/toolkits/delighted/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/delighted/framework/cli) - [Google ADK](https://composio.dev/toolkits/delighted/framework/google-adk) - [LangChain](https://composio.dev/toolkits/delighted/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/delighted/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/delighted/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/delighted/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/delighted/framework/crew-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 Delighted - Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams - Configure an Autogen AssistantAgent that can call Delighted tools - Run a live chat loop where you ask the agent to perform Delighted 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 Delighted MCP server, and what's possible with it? The Delighted MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Delighted account. It provides structured and secure access so your agent can perform Delighted operations on your behalf. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `DELIGHTED_ADD_PERSON_TO_AUTOPILOT_EMAIL` | Add Person to Autopilot Email | Tool to add a person to Autopilot or update their properties for email-based surveys. Use when you need to enroll a person in scheduled email surveys or update their custom properties. | | `DELIGHTED_ADD_PERSON_TO_AUTOPILOT_SMS` | Add Person to Autopilot SMS | Tool to add a person to Autopilot or update their properties for SMS-based surveys. Use when you need to schedule automated survey delivery via SMS. | | `DELIGHTED_CREATE_PERSON` | Create or Update Person | Tool to create or update a person and schedule a survey email. Use when you need to add a new person to Delighted, update existing person details, or schedule a survey with custom properties for segmentation. | | `DELIGHTED_DELETE_PENDING_SURVEY_REQUESTS` | Delete Pending Survey Requests | Tool to remove all pending (scheduled but not yet sent) survey requests for a person. Use when you need to cancel all future surveys for a specific email address. | | `DELIGHTED_DELETE_PERSON` | Delete Person | Tool to remove a person and all associated data from Delighted. Use when you need to permanently delete a person's information. Deletion includes surveys, responses, properties, Autopilot membership, survey history, and unsubscribe/bounce status. | | `DELIGHTED_GET_AUTOPILOT_EMAIL_CONFIGURATION` | Get Autopilot Email Configuration | Tool to retrieve the current Autopilot configuration for email distribution. Returns configuration details including whether Autopilot is active, survey frequency, and timestamps. | | `DELIGHTED_GET_AUTOPILOT_SMS_CONFIGURATION` | Get Autopilot SMS Configuration | Tool to retrieve the current Autopilot configuration for SMS distribution. Use when you need to check whether Autopilot is enabled, review survey frequency settings, or examine configuration timestamps for SMS surveys. | | `DELIGHTED_LIST_AUTOPILOT_SMS_MEMBERSHIPS` | List Autopilot SMS Memberships | Tool to retrieve all Autopilot memberships for SMS distribution platform. Use when you need to list people enrolled in Autopilot SMS or filter by specific person details. | | `DELIGHTED_LIST_BOUNCED_PEOPLE` | List Bounced People | Tool to retrieve all bounced people for your account, ordered by bounce time (oldest first). Use when you need to identify email addresses that have bounced. Supports pagination via per_page and page parameters, and optional Unix timestamp filters (since, until) to restrict results to specific time ranges. | | `DELIGHTED_LIST_PEOPLE` | List People | Tool to retrieve all people for your account in creation order. Use when you need to list contacts, filter by email or phone number, or paginate through your people database. Supports cursor-based pagination via Link header and optional time-based filtering. Note: email and phone_number filters are mutually exclusive. | | `DELIGHTED_LIST_SURVEY_RESPONSES` | List Survey Responses | Tool to retrieve all survey responses for your account with pagination support and optional filtering. Use when you need to access survey feedback data, filter by date range, trend, person, or sort by creation/update time. Supports expanding person details and notes. | | `DELIGHTED_LIST_UNSUBSCRIBED_PEOPLE` | List Unsubscribed People | Tool to retrieve all unsubscribed people for your account, ordered by unsubscribe time (oldest first). Use when you need to identify people who have unsubscribed. Supports pagination via per_page and page parameters, and optional Unix timestamp filters (since, until) to restrict results to specific time ranges. | | `DELIGHTED_UNSUBSCRIBE_PERSON` | Unsubscribe Person | Tool to add a person to your unsubscribe list, preventing them from receiving any future surveys via email. Use when you need to permanently unsubscribe someone from all email surveys. This is functionally equivalent to the person clicking Unsubscribe within a survey. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Delighted MCP server is an implementation of the Model Context Protocol that connects your AI agents and assistants directly to Delighted. Instead of manually wiring Delighted 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 Delighted 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 Delighted 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 Delighted 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 Delighted 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 Delighted session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["delighted"] ) 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 Delighted 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 Delighted assistant agent with MCP tools agent = AssistantAgent( name="delighted_assistant", description="An AI assistant that helps with Delighted 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 Delighted 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 Delighted 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 Delighted session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["delighted"] ) 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 Delighted assistant agent with MCP tools agent = AssistantAgent( name="delighted_assistant", description="An AI assistant that helps with Delighted 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 Delighted 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 Delighted 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 Delighted, you can reuse the same structure for other MCP-enabled apps with minimal code changes. ## How to build Delighted MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/delighted/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/delighted/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/delighted/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/delighted/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/delighted/framework/codex) - [OpenClaw](https://composio.dev/toolkits/delighted/framework/openclaw) - [Hermes](https://composio.dev/toolkits/delighted/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/delighted/framework/cli) - [Google ADK](https://composio.dev/toolkits/delighted/framework/google-adk) - [LangChain](https://composio.dev/toolkits/delighted/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/delighted/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/delighted/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/delighted/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/delighted/framework/crew-ai) ## Related Toolkits - [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly. - [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place. - [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations. - [Asana](https://composio.dev/toolkits/asana) - Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals. - [Google Tasks](https://composio.dev/toolkits/googletasks) - Google Tasks is a to-do list and task management tool integrated into Gmail and Google Calendar. It helps you organize, track, and complete tasks across your Google ecosystem. - [Linear](https://composio.dev/toolkits/linear) - Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity. - [Firecrawl](https://composio.dev/toolkits/firecrawl) - Firecrawl automates large-scale web crawling and data extraction. It helps organizations efficiently gather, index, and analyze content from online sources. - [Tavily](https://composio.dev/toolkits/tavily) - Tavily offers powerful search and data retrieval from documents, databases, and the web. It helps teams locate and filter information instantly, saving hours on research. - [Jira](https://composio.dev/toolkits/jira) - Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently. - [Exa](https://composio.dev/toolkits/exa) - Exa is a data extraction and search platform for gathering and analyzing information from websites, APIs, or databases. It helps teams quickly surface insights and automate data-driven workflows. - [Serpapi](https://composio.dev/toolkits/serpapi) - SerpApi is a real-time API for structured search engine results. It lets you automate SERP data collection, parsing, and analysis for SEO and research. - [Clickup](https://composio.dev/toolkits/clickup) - ClickUp is an all-in-one productivity platform for managing tasks, docs, goals, and team collaboration. It streamlines project workflows so teams can work smarter and stay organized in one place. - [Monday](https://composio.dev/toolkits/monday) - Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time. - [Peopledatalabs](https://composio.dev/toolkits/peopledatalabs) - Peopledatalabs delivers B2B data enrichment and identity resolution APIs. Supercharge your apps with accurate, up-to-date business and contact data. - [Snowflake](https://composio.dev/toolkits/snowflake) - Snowflake is a cloud data warehouse built for elastic scaling, secure data sharing, and fast SQL analytics across major clouds. - [Posthog](https://composio.dev/toolkits/posthog) - PostHog is an open-source analytics platform for tracking user interactions and product metrics. It helps teams refine features, analyze funnels, and reduce churn with actionable insights. - [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time. - [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. - [Agiled](https://composio.dev/toolkits/agiled) - Agiled is an all-in-one business management platform for CRM, projects, and finance. It helps you streamline workflows, consolidate client data, and manage business processes in one place. - [Amplitude](https://composio.dev/toolkits/amplitude) - Amplitude is a digital analytics platform for product and behavioral data insights. It helps teams analyze user journeys and make data-driven decisions quickly. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Delighted MCP? With a standalone Delighted MCP server, the agents and LLMs can only access a fixed set of Delighted tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Delighted 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 Delighted tools. ### Can I manage the permissions and scopes for Delighted while using Tool Router? Yes, absolutely. You can configure which Delighted 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 Delighted data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)