How to Use the Biconomy (Account Abstraction) MCP in Pydantic AI

Q: How does the server protect my sensitive Web3 signature data?

All signature payloads processed by executesupertx are handled in memory within an ephemeral V8 isolate. Vinkius does not log or persist your raw signature strings, keeping your cryptographic data completely private.

Run type-safe Biconomy (Account Abstraction) transactions with runtime validation using Pydantic AI and this 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 Pydantic AI

Create your Vinkius account to connect Biconomy (Account Abstraction) to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute transactions with strict runtime validation

`execute_supertx` is the tool that submits your signed payloads to the network, and Pydantic AI ensures the response matches your strict schema. If the transaction receipt contains unexpected fields, the framework raises a validation error immediately instead of letting silent data corruption pass. This strictness is crucial when dealing with real funds. By forcing every step of the transaction cycle to validate against Pydantic models, you eliminate the risk of your agent acting on malformed on-chain data.

Validate gas quotes before signing

`get_quote` pulls pricing and payload data from the relayer, which Pydantic AI parses into strongly typed Python objects. Your agent can immediately check if the quoted gas fees exceed your predefined limits before generating a signature. Because the framework is model-agnostic, you can use this validation logic with any LLM. The type checks run locally in your Python environment, guaranteeing that your agent never signs an over-priced transaction due to model hallucination.

Track transaction status using this MCP Server

`get_explorer_status` provides real-time updates on your transaction's journey on-chain, validated at every turn by your Pydantic AI agent. The tool returns structured status data that your Python code can safely parse without worrying about unexpected null values. This gives you a reliable way to build loops that poll for transaction completion. If the network returns a state your schema doesn't expect, your application fails loudly, alerting your team before any state mismatch occurs.

Setup guide

Set up Biconomy (Account Abstraction) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "biconomy-account-abstraction-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Biconomy (Account Abstraction) tools.",
)

result = await agent.run("List recent Biconomy (Account Abstraction) transactions")
print(result.output)

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 Pydantic AI

Install the slim package with MCP support, then initialize MCPToolset pointing to your Vinkius HTTP endpoint. Pass this toolset directly into the toolsets list of your Pydantic AI Agent.

It prevents silent failures by validating every quote and transaction payload against strict Python types at runtime. If the blockchain or the relayer returns unexpected data, your agent halts immediately.

No, you must use the unified MCPToolset constructor. The older MCPServerHTTP client is deprecated and will not work with the current Vinkius streaming endpoints.

Yes, Pydantic AI is completely model-agnostic. You can connect your Biconomy tools to local models running via Ollama or enterprise APIs like Anthropic and OpenAI.

All signature payloads processed by execute_supertx are handled in memory within an ephemeral V8 isolate. Vinkius does not log or persist your raw signature strings, keeping your cryptographic data completely private.

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