How to Use the Biconomy (Account Abstraction) MCP in LangChain

Q: How do I get quotes using Biconomy (Account Abstraction) in LangChain?

You call getquote within your chain to request a Supertransaction quote. The agent parses the returned payload and prepares it for signing. This happens in a single step before execution.

Q: Can LangChain execute a Biconomy (Account Abstraction) transaction directly?

Yes, the agent uses executesupertx to submit the signed payload. You must ensure the signatures are correctly appended to the payloadToSign field inside the quote object. The MCP Server handles the actual transmission to the Biconomy relayer.

Q: What is the best way to track transaction status with Biconomy (Account Abstraction) and LangChain?

Use the getexplorerstatus tool to poll the execution state. Your agent checks this status to confirm the transaction cleared before triggering the next chain link.

Chain Biconomy transaction quotes and executions directly inside your LangChain agents without writing custom Web3 integration code.

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 LangChain

Create your Vinkius account to connect Biconomy (Account Abstraction) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch and sign transaction quotes with LangChain

The `get_quote` tool gets a Supertransaction quote directly from the Biconomy protocol. Your agent takes the output payload, prompts the user or a local wallet for signatures, and prepares the final payload for execution. Passing this data through a LangChain runnable ensures that the gas estimates and execution paths are locked in before you proceed to the next step. You avoid manual JSON parsing because the schema feeds directly into the next agent step.

Execute Supertransactions via LangChain MCP Server

The `execute_supertx` tool takes your signed quote object and executes the transaction on-chain. You must provide the full quote object with your signatures appended to the `payloadToSign` field. By integrating this into a ReAct loop, your agent verifies the transaction structure before sending it. LangSmith traces the entire payload transfer, giving you a clear view of exactly what went to the blockchain.

Track execution status in real-time

The `get_explorer_status` tool monitors the progress of your submitted Supertransaction. It queries the Biconomy explorer to verify if the transaction succeeded, failed, or remains pending. Your agent uses this status to decide whether to retry or proceed with subsequent chain steps. This keeps your automated workflows moving forward without manual intervention or polling scripts.

Setup guide

Set up Biconomy (Account Abstraction) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Biconomy (Account Abstraction) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "biconomy-account-abstraction-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Biconomy (Account Abstraction) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You call `get_quote` within your chain to request a Supertransaction quote. The agent parses the returned payload and prepares it for signing. This happens in a single step before execution.

Yes, the agent uses `execute_supertx` to submit the signed payload. You must ensure the signatures are correctly appended to the `payloadToSign` field inside the quote object. The MCP Server handles the actual transmission to the Biconomy relayer.

Use the `get_explorer_status` tool to poll the execution state. Your agent checks this status to confirm the transaction cleared before triggering the next chain link.

The server exposes the tools to your agent, which evaluates the output of `get_quote` before deciding to call `execute_supertx`. This lets your agent handle failures or price changes dynamically.

Your private keys never touch this MCP Server. The server only receives the already-signed quote object and transmits it to Biconomy. All signing happens locally within your secure client environment.

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