How to Use the Biconomy (Account Abstraction) MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK setup handle gasless transactions using Biconomy (Account Abstraction)?

Yes, your agent queries getquote to fetch the transaction details and then dispatches the signed payload via executesupertx. The Biconomy paymaster handles the gas fees on the back end, so your users do not need native tokens.

Run gasless transactions and batched execution directly inside OpenAI Agents SDK with this secure MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Biconomy (Account Abstraction) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Biconomy (Account Abstraction) to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Biconomy (Account Abstraction) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Batch transactions with OpenAI Agents SDK

`execute_supertx` is the tool your agent runs when it needs to sign and dispatch complex multi-step transactions in a single shot. Your OpenAI Agents SDK workflow passes the signed payload directly to this endpoint, completely bypassing the need for manual gas management or sequential execution loops. The agent handles the execution on-chain while the OpenAI dashboard traces every step of the payload transit. If a transaction fails mid-flight, the SDK's built-in guardrails catch the error before it hits your production logs, saving you hours of debugging.

Fetch real-time gas quotes on the fly

`get_quote` pulls exact pricing data for multi-chain operations directly into your agent's runtime. Instead of hardcoding gas limits, your OpenAI Agents SDK setup queries this tool to get a precise quote, which your safety guardrails validate before signing. Having this real-time pricing data means your agent can automatically choose the cheapest relayer without human intervention. This keeps your operating costs predictable while running complex account abstraction logic behind the scenes.

Track execution state via the MCP Server

`get_explorer_status` monitors the exact state of your dispatched supertransactions so your agent knows when to proceed. Your OpenAI Agents SDK setup polls this tool to confirm on-chain settlement before handing off the task to another specialized agent. This direct feedback loop prevents your agent system from getting stuck in a black box. You see the exact transaction hash and status directly inside your tracing dashboard, giving you full visibility into your automated Web3 operations.

Setup guide

Set up Biconomy (Account Abstraction) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Biconomy (Account Abstraction) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Biconomy (Account Abstraction) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Biconomy (Account Abstraction) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Biconomy (Account Abstraction) Agent",
            instructions="You have access to Biconomy (Account Abstraction) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Biconomy. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Biconomy (Account Abstraction) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Biconomy (Account Abstraction) MCP in OpenAI Agents SDK

Install the package using pip install openai-agents. Next, instantiate the MCPServerStreamableHttp client with your hosted MCP server endpoint URL and pass it into your Agent constructor using the mcp_servers list.

Yes, your agent queries get_quote to fetch the transaction details and then dispatches the signed payload via execute_supertx. The Biconomy paymaster handles the gas fees on the back end, so your users do not need native tokens.

You define validation schemas inside your agent configuration to check the payloads returned by get_quote before signing. This prevents the agent from executing unauthorized on-chain actions or sending funds to unverified addresses.

No, the SDK automatically discovers all three tools from the hosted MCP server at runtime. Setting cacheToolsList=True ensures your agent does not waste time fetching the tool definitions on every single turn.

Your raw private keys never touch the Vinkius infrastructure. The server only processes signed transaction payloads and public address queries, which are routed through secure, ephemeral V8 isolates that discard all execution data immediately after the on-chain status is returned.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript