How to integrate Alchemy MCP with OpenAI Agents SDK

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Alchemy logo
OpenAI Agents SDK logo
divider

Introduction

This guide walks you through connecting Alchemy to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Alchemy agent that can show all nfts owned by this wallet, get recent sales for a specific nft collection, check erc20 token balances for your address through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Alchemy account through Composio's Alchemy MCP server.

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

Also integrate Alchemy with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Alchemy
  • Configure an AI agent that can use Alchemy as a tool
  • Run a live chat session where you can ask the agent to perform Alchemy operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

What is the Alchemy MCP server, and what's possible with it?

The Alchemy MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Alchemy account. It provides structured and secure access to your blockchain data, so your agent can perform actions like fetching NFT metadata, tracking token balances, analyzing transaction history, and managing Ethereum assets on your behalf.

  • Retrieve NFT contract and token metadata: Instantly access detailed information about any NFT collection or token, including name, symbol, supply, and contract deployer.
  • Analyze NFT sales and ownership: Let your agent fetch historical NFT sales across marketplaces and list current owners for any ERC-721 or ERC-1155 token.
  • Track token balances and portfolio: Effortlessly check ERC-20 token balances for any Ethereum address to monitor holdings or build portfolio analytics.
  • List NFTs within a collection: Pull a complete list of NFTs under a specific contract to explore, display, or analyze full collections.
  • Monitor transaction counts and activity: Quickly get the transaction count (nonce) for any Ethereum address to understand activity or prepare for new transactions.

Supported Tools & Triggers

Tools
Compute NFT RarityTool to compute the rarity of each attribute for a specific NFT based on its collection.
Get NFT Collection MetadataTool to get metadata for an NFT collection using its marketplace slug (OpenSea, LooksRare, etc).
Get Collections for OwnerTool to retrieve all NFT collections held by a specified owner address.
Get Contract Metadata Batch V3Tool to retrieve metadata for multiple NFT contracts in a single batch request.
Get Contract Metadata V3Tool to get the metadata for an NFT contract including name, symbol, total supply, and token type (ERC721/ERC1155).
Get Contracts for Owner (NFT API v3)Tool to get all NFT contracts owned by an address with contract metadata.
Get NFT Floor PriceTool to get the floor price for an NFT collection across multiple marketplaces (OpenSea, LooksRare, etc).
Get Historical Token PricesRetrieves historical price data for a token over a specified time range with configurable intervals.
Get NFT Contracts By AddressTool to retrieve NFT contracts associated with one or more wallet addresses across multiple blockchain networks.
Get NFT MetadataTool to retrieve comprehensive metadata for a specific NFT, including contract details, media URLs, attributes, ownership info, and OpenSea data.
Get NFT Metadata BatchTool to retrieve metadata for multiple NFTs in a single request (up to 100 NFTs), including contract details, media URLs, attributes, and collection data.
Get NFT Sales V3Retrieves NFT sales that have occurred through on-chain marketplaces using Alchemy's v3 API.
Get NFTs for Collection V3Retrieves all NFTs in a collection using OpenSea collection slug or contract address.
Get NFTs for ContractRetrieves all NFTs for a given NFT contract address.
Get NFTs for OwnerTool to get all NFTs currently owned by a given address.
Get Owners for CollectionTool to retrieve all owner addresses for a given NFT collection contract.
Get Owners for ContractTool to get all owners of NFTs in a contract with optional token balances.
Get NFT Owners (v3)Tool to retrieve all owners for a specific NFT using Alchemy's v3 API.
Get Portfolio NFTs By AddressTool to fetch NFTs owned by multiple wallet addresses across different blockchain networks.
Get Token Prices By SymbolTool to get current token prices by symbol (e.
Get Token BalancesThis tool retrieves ERC20 token balances for a specified Ethereum address.
Get Token Balances By AddressTool to get token balances for wallet addresses across multiple networks using Alchemy's Portfolio API.
Get Token MetadataRetrieves metadata for an ERC-20 token on Ethereum mainnet, including its name, symbol, decimals, and logo URL.
Get Token Prices By AddressRetrieves current token prices by contract address and network from decentralized exchanges (DEXes).
Get Tokens By AddressTool to fetch fungible tokens (native, ERC-20, SPL) for multiple wallet addresses across networks.
Get Transaction CountThis tool retrieves the number of transactions sent from a specific address (also known as the nonce).
Get Transactions History By AddressTool to get transaction history for wallet addresses across multiple networks using Alchemy's Data API.
Invalidate NFT Contract CacheTool to invalidate the cached metadata for an NFT contract.
Check If NFT Is AirdropTool to check if a specific NFT token is marked as an airdrop.
Check If NFT Is AirdropTool to determine whether an NFT was airdropped to the owner address.
Check Collection OwnershipTool to check if a wallet address owns any token from a specific NFT collection.
Check NFT Holder StatusTool to check if a wallet address holds any NFTs from a specific contract.
Check if Contract is SpamTool to check if an NFT contract is marked as spam by Alchemy.
Check if Contract is Spam (V3)Tool to determine if a specific NFT contract is marked as spam by Alchemy.
Search NFT Contract MetadataTool to search for keywords across metadata of all ERC-721 and ERC-1155 smart contracts.
Summarize NFT AttributesRetrieves a comprehensive summary of all attributes and traits for NFTs in a collection, including trait counts and distribution statistics.

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

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Alchemy project
  • Some knowledge of Python or Typescript

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Alchemy.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Alchemy Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["alchemy"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only alchemy.
  • The router checks the user's Alchemy connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Alchemy.
  • This approach keeps things lightweight and lets the agent request Alchemy tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Alchemy. "
        "Help users perform Alchemy operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Alchemy and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Alchemy operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Alchemy.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Alchemy and OpenAI Agents SDK:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["alchemy"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Alchemy. "
        "Help users perform Alchemy operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Alchemy MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Alchemy.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Alchemy MCP Agent with another framework

Claude Agent SDK logo

Claude Agent SDK

Use Alchemy MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Alchemy MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Alchemy MCP with Claude Cowork

Codex logo

Codex

Use Alchemy MCP with Codex

OpenClaw logo

OpenClaw

Use Alchemy MCP with OpenClaw

Hermes logo

Hermes

Use Alchemy MCP with Hermes

CLI logo

CLI

Use Alchemy MCP with CLI

Google ADK logo

Google ADK

Use Alchemy MCP with Google ADK

LangChain logo

LangChain

Use Alchemy MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Alchemy MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Alchemy MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Alchemy MCP with LlamaIndex

CrewAI logo

CrewAI

Use Alchemy MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Alchemy MCP?

With a standalone Alchemy MCP server, the agents and LLMs can only access a fixed set of Alchemy tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Alchemy and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK 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 Alchemy tools.

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

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

Used by agents from

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

Get started for freeGet a demo↗