# How to integrate Mem MCP with Autogen ```json { "title": "How to integrate Mem MCP with Autogen", "toolkit": "Mem", "toolkit_slug": "mem", "framework": "AutoGen", "framework_slug": "autogen", "url": "https://composio.dev/toolkits/mem/framework/autogen", "markdown_url": "https://composio.dev/toolkits/mem/framework/autogen.md", "updated_at": "2026-05-12T10:18:38.393Z" } ``` ## Introduction This guide walks you through connecting Mem to AutoGen using the Composio tool router. By the end, you'll have a working Mem agent that can create a new note about today's meeting, organize research notes into a project collection, delete last week's outdated task note through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Mem account through Composio's Mem MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Mem with - [OpenAI Agents SDK](https://composio.dev/toolkits/mem/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/mem/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/mem/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/mem/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/mem/framework/codex) - [OpenClaw](https://composio.dev/toolkits/mem/framework/openclaw) - [Hermes](https://composio.dev/toolkits/mem/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/mem/framework/cli) - [Google ADK](https://composio.dev/toolkits/mem/framework/google-adk) - [LangChain](https://composio.dev/toolkits/mem/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/mem/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/mem/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/mem/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/mem/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 Mem - Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams - Configure an Autogen AssistantAgent that can call Mem tools - Run a live chat loop where you ask the agent to perform Mem 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 Mem MCP server, and what's possible with it? The Mem MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mem account. It provides structured and secure access to your notes and collections, so your agent can perform actions like creating notes, organizing collections, retrieving note content, and deleting outdated information on your behalf. - Automated note creation: Ask your agent to quickly capture ideas, meeting summaries, or research notes and save them directly into your Mem workspace. - Organize with collections: Direct your agent to group related notes by creating new collections for projects, topics, or teams, keeping your knowledge base tidy and efficient. - Retrieve and review notes: Let your agent fetch the content and metadata of any note by its identifier, making it easy to reference or summarize past information. - Cleanup and delete notes or collections: Instruct your agent to remove outdated notes or entire collections for a clutter-free knowledge base. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `MEM_CREATE_COLLECTION` | Create Collection | Creates a new collection in Mem for organizing and grouping related notes. Collections are containers that help categorize notes by topic, project, or any organizational scheme. Each collection has a title and optional description. Use this action when you need to: - Create a new organizational container for notes - Set up a project workspace with a descriptive title - Organize notes by category or theme Returns the created collection's details including its unique ID. | | `MEM_CREATE_NOTE_V2` | Create Note V2 | Tool to create a new note with markdown content and optional collection associations. The first line of content is automatically interpreted as the title. Use when you need to create a note and optionally add it to one or more collections by ID or title. | | `MEM_DELETE_COLLECTION` | Delete Collection | Tool to permanently delete a Mem collection. Deletion is irreversible — only invoke after explicit user confirmation and verification of the correct collection_id. | | `MEM_DELETE_NOTE` | Delete Note | Tool to permanently delete a specific note. Deletion is irreversible — obtain explicit user confirmation before calling. Use when you need to remove a note by its unique identifier after confirming the note_id. | | `MEM_GET_COLLECTION` | Get Collection | Retrieve the details of a Mem collection by its UUID. Returns the collection's title, description, and timestamps. Use this when you need to fetch metadata for a specific collection. | | `MEM_LIST_COLLECTIONS` | List Collections | List collections with pagination support. Returns collections sorted by updated_at or created_at. Use this action to retrieve all collections or browse through collections page by page. | | `MEM_LIST_NOTES` | List Notes | Tool to list notes with pagination and filtering options. Supports filtering by collection, task presence, image presence, and file presence. Use when you need to retrieve multiple notes or search for notes matching specific criteria. | | `MEM_READ_NOTE` | Read Note | Retrieve the content and metadata of a Mem note by its UUID. Returns the note's title, markdown content, timestamps, and collection membership. Use this when you need to read or display an existing note's content. | | `MEM_SAVE_CONTENT` | Save Content | Tool to process and remember any raw content using AI. Accepts web pages, emails, transcripts, articles, or simple text. Use when you want to save and process content with optional instructions on how to process it and context about how it relates to existing knowledge. | | `MEM_SEARCH_COLLECTIONS` | Search Collections | Tool to search collections using an optional query string. Use when you need to find or list collections by title or description. | | `MEM_SEARCH_NOTES` | Search Notes | Tool to search notes in Mem using a query string with optional filtering. Supports filtering by collection IDs, task presence, image presence, and file presence. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Mem MCP server is an implementation of the Model Context Protocol that connects your AI agents and assistants directly to Mem. Instead of manually wiring Mem 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 Mem 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 Mem 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 Mem 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 Mem 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 Mem session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["mem"] ) 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 Mem 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 Mem assistant agent with MCP tools agent = AssistantAgent( name="mem_assistant", description="An AI assistant that helps with Mem 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 Mem 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 Mem 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 Mem session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["mem"] ) 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 Mem assistant agent with MCP tools agent = AssistantAgent( name="mem_assistant", description="An AI assistant that helps with Mem 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 Mem 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 Mem 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 Mem, you can reuse the same structure for other MCP-enabled apps with minimal code changes. ## How to build Mem MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/mem/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/mem/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/mem/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/mem/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/mem/framework/codex) - [OpenClaw](https://composio.dev/toolkits/mem/framework/openclaw) - [Hermes](https://composio.dev/toolkits/mem/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/mem/framework/cli) - [Google ADK](https://composio.dev/toolkits/mem/framework/google-adk) - [LangChain](https://composio.dev/toolkits/mem/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/mem/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/mem/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/mem/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/mem/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. - [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. - [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. - [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. - [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. - [Ascora](https://composio.dev/toolkits/ascora) - Ascora is a cloud-based field service management platform for service businesses. It streamlines scheduling, invoicing, and customer operations in one place. - [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place. - [Beeminder](https://composio.dev/toolkits/beeminder) - Beeminder is an online goal-tracking platform that uses monetary pledges to keep you motivated. Stay accountable and hit your targets with real financial incentives. - [Boxhero](https://composio.dev/toolkits/boxhero) - Boxhero is a cloud-based inventory management platform for SMBs, offering real-time updates, barcode scanning, and team collaboration. It helps businesses streamline stock tracking and analytics for smarter inventory decisions. - [Breathe HR](https://composio.dev/toolkits/breathehr) - Breathe HR is cloud-based HR software for SMEs to manage employee data, absences, and performance. It simplifies HR admin, making it easy to keep employee records accurate and up to date. - [Breeze](https://composio.dev/toolkits/breeze) - Breeze is a project management platform designed to help teams plan, track, and collaborate on projects. It streamlines workflows and keeps everyone on the same page. - [Bugherd](https://composio.dev/toolkits/bugherd) - Bugherd is a visual feedback and bug tracking tool for websites. It helps teams and clients report website issues directly on live sites for faster fixes. - [Canny](https://composio.dev/toolkits/canny) - Canny is a platform for managing customer feedback and feature requests. It helps teams prioritize product decisions based on real user insights. - [Chmeetings](https://composio.dev/toolkits/chmeetings) - Chmeetings is a church management platform for events, members, donations, and volunteers. It streamlines church operations and improves community engagement. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Mem MCP? With a standalone Mem MCP server, the agents and LLMs can only access a fixed set of Mem tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Mem 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 Mem tools. ### Can I manage the permissions and scopes for Mem while using Tool Router? Yes, absolutely. You can configure which Mem 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 Mem data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)