How to integrate Supermemory MCP with Autogen

This guide walks you through connecting Supermemory to AutoGen using the Composio tool router. By the end, you'll have a working Supermemory agent that can store your documents, search your memories, recall saved context, and update documents through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Supermemory account through Composio's Supermemory 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
Supermemory logoSupermemory
Api Key

Supermemory is a memory and context API for ingesting, organizing, searching, and recalling information. Use it to give apps durable, searchable context without rebuilding memory infrastructure.

11 Tools

Introduction

This guide walks you through connecting Supermemory to AutoGen using the Composio tool router. By the end, you'll have a working Supermemory agent that can store your documents, search your memories, recall saved context, and update documents through natural language commands.

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

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

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

The Supermemory MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Supermemory account. It provides structured and secure access to your documents, memories, learned profiles, and account usage, so your agent can ingest information, organize documents, search context, recall memories, and review usage on your behalf.

  • Document ingestion and organization: Have your agent add text, public web content, or document collections, then organize them with containers, metadata, and file paths.
  • Memory and context search: Instruct your agent to search memories, document content, or both by meaning, with optional container and metadata filters.
  • Document review and management: Let the agent list documents, inspect their content and processing status, review extracted chunks, update stored information, or delete documents.
  • Memory and profile recall: Direct your agent to list extracted memories or retrieve learned profiles for a container, with matching search results when needed.
  • Account usage checks: Have your agent review your Supermemory plan, credit balance, overall usage, and reset date.

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

Supported Tools

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

Add Document

Ingest text or a public URL as a Supermemory document and return its document ID and initial processing status.

Add Documents

Add 1 to 600 documents in one request, with explicit per-document metadata and processing options.

Delete Document

Permanently delete one document by ID.

Get Account Status

Return the connected Supermemory organization's plan, credit balance, high-level usage, and reset date.

Get Document

Get one document's content, metadata, source details, and processing status by document ID.

Get Document Chunks

Return the ordered extracted chunks for one processed document.

Get Profile

Retrieve the static, dynamic, or bucketed profile learned for one container tag, optionally with matching search results.

List Documents

List documents, optionally filtered by containers, metadata, or filepath, one page at a time.

List Memories

List extracted memory entries for one or more container tags, one page at a time.

Search Memory

Semantically search Supermemory memories, document chunks, or both, with optional container and metadata filters.

Update Document

Update the content, metadata, container, or processing configuration of one existing document.

FRAMEWORKS

How to build Supermemory MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Supermemory MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Supermemory MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Supermemory MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Supermemory MCP with Claude Cowork

Codex logo

Codex

Use Supermemory MCP with Codex

OpenClaw logo

OpenClaw

Use Supermemory MCP with OpenClaw

Hermes logo

Hermes

Use Supermemory MCP with Hermes

CLI logo

CLI

Use Supermemory MCP with CLI

Google ADK logo

Google ADK

Use Supermemory MCP with Google ADK

LangChain logo

LangChain

Use Supermemory MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Supermemory MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Supermemory MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Supermemory MCP with LlamaIndex

CrewAI logo

CrewAI

Use Supermemory MCP with CrewAI

FAQ

Frequently asked questions

With a standalone Supermemory MCP server, the agents and LLMs can only access a fixed set of Supermemory tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Supermemory 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 Supermemory tools.

Yes, absolutely. You can configure which Supermemory 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 Supermemory data and credentials are handled as safely as possible.

Start with Supermemory.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Supermemory 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