How to integrate Open sea MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Open sea Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Open sea to AutoGen using the Composio tool router. By the end, you'll have a working Open sea agent that can list my nft for sale on opensea, show all active listings in bored ape collection, create an offer for a specific cryptopunk, fetch my opensea profile details through natural language commands.

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

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

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

The Open sea MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your OpenSea account. It provides structured and secure access to your NFT marketplace activity, so your agent can perform actions like listing NFTs for sale, creating and fulfilling offers, checking account details, and managing your marketplace orders on your behalf.

  • NFT listing automation: Quickly list any ERC721 or ERC1155 NFT for sale on OpenSea, specifying price and collection details—all handled by your agent.
  • Offer creation and management: Instruct your agent to create criteria-based or single-item offers to purchase specific NFTs or those matching certain traits within a collection.
  • Order and listing fulfillment: Let your agent retrieve all necessary information and signatures to fulfill existing listings or offers, making transactions seamless and secure.
  • Marketplace activity insights: Have the agent pull your profile details, fetch all active listings or offers for a given collection, and provide you with up-to-date marketplace snapshots.
  • Order cancellation and management: Direct your agent to cancel open orders, listings, or offers off-chain, helping you stay in control of your marketplace participation with ease.

Supported Tools & Triggers

Tools
Build criteria offerBuild a portion of a criteria offer including the merkle tree needed to post an offer.
Cancel orderOffchain cancel a single order, offer or listing, by its order hash when protected by the signedzone.
Create criteria offerCreate a criteria offer to purchase any nft in a collection or which matches the specified trait.
Create item offerCreate an offer to purchase a single nft (erc721 or erc1155).
Create listingList a single nft (erc721 or erc1155) for sale on the opensea marketplace.
Fulfill listingRetrieve all the information, including signatures, needed to fulfill a listing directly onchain.
Fulfill offerRetrieve all the information, including signatures, needed to fulfill an offer directly onchain.
Get accountGet an opensea account profile including details such as bio, social media usernames, and profile image.
Get all listings by collectionGet all active, valid listings for a single collection.
Get all offers by collectionGet all active, valid offers for the specified collection.
Get best listing by nftGet the best listing for an nft.
Get best listings by collectionGet the cheapest priced active, valid listings on a single collection.
Get best offer by nftGet the best offers for an nft.
Get collectionGet a single collection including details such as fees, traits, and links.
Get collectionsGet a list of opensea collections with optional filtering and pagination.
Get collection statsGet stats for a single collection on opensea.
Get contractGet a smart contract for a given chain and address.
Get eventsGet a list of events from opensea based on various filters like timestamps and event types.
Get listingsGet the complete set of active, valid listings.
Get nftGet metadata, traits, ownership information, and rarity for a single nft.
Get orderGet a single order, offer or listing, by its order hash.
Get payment tokenGet a smart contract for a given chain and address.
Get traitsGet the traits in a collection.
Refresh nft metadataRefresh metadata for a single nft.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router 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 Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router 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

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Open sea account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

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.

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 Open sea via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

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 Open sea connections to use

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 Open sea session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["open_sea"]
    )
    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 Open sea tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

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

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 Open sea assistant agent with MCP tools
    agent = AssistantAgent(
        name="open_sea_assistant",
        description="An AI assistant that helps with Open sea 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 Open sea tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Open sea 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 Open sea 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 Open sea 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 Open sea session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["open_sea"]
    )
    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 Open sea assistant agent with MCP tools
        agent = AssistantAgent(
            name="open_sea_assistant",
            description="An AI assistant that helps with Open sea 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 Open sea 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 Open sea 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 Open sea, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Open sea MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Open sea MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Open sea MCP with Claude Agent SDK

Google ADK

Google ADK

Use Open sea MCP with Google ADK

LangChain

LangChain

Use Open sea MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Open sea MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Open sea MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Open sea MCP with LlamaIndex

CrewAI

CrewAI

Use Open sea MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Open sea MCP?

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

Can I manage the permissions and scopes for Open sea while using Tool Router?

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

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free