How to Use the Dynamic (Web3 Auth) MCP in OpenAI Agents SDK

Q: How do I configure Dynamic (Web3 Auth) with the OpenAI Agents SDK?

Install the package, initialize MCPServerStreamableHttp with your Vinkius endpoint, and register it in the mcpservers list of your Agent constructor. Setting cacheToolsList=True ensures your agent discovers the tools without extra network roundtrips.

Q: Can the OpenAI Agents SDK handle multi-agent handoffs based on Dynamic (Web3 Auth) balances?

Yes, your routing agent can call gettokenbalances and use the returned profile to hand off the conversation to a specialized premium agent if the wallet meets your threshold. This keeps your logic modular and secure.

Q: Does the Dynamic (Web3 Auth) integration support automated session revocation in OpenAI Agents SDK?

Yes, you can program your agent to trigger revokesession based on custom safety guardrails in your Python code. This allows the OpenAI Agents SDK to actively kick out compromised users.

Q: How do we track webhook events from this setup?

Use the getwebhooks and geteventtypes tools to query your active endpoints. Your agent can read these configurations directly to verify that your Web3 auth events are routing to the correct backend handlers.

Secure your Web3 user auth and sanctions checks inside production OpenAI Agents SDK workflows with this managed 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 Dynamic (Web3 Auth) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Dynamic (Web3 Auth) 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 Dynamic (Web3 Auth) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Compliance Guardrails for Wallets

The `check_sanctions` tool verifies wallet addresses against global blocklists directly inside your OpenAI Agents SDK run loop. Your agent checks compliance status before initiating any transfer or handoff, halting operations instantly if a wallet is flagged. By integrating this check into your guardrail layer, you prevent illicit transactions before they hit the blockchain. The OpenAI dashboard logs every check, ensuring you have a clean audit trail of your automated compliance decisions.

Direct Profile and Balance Checks

The `get_user` and `get_token_balances` tools pull Web3 profiles and live assets into your OpenAI Agents SDK session context. Your agent inspects token holdings to verify eligibility before routing the user to high-value transaction steps. This setup lets you skip building custom RPC pipelines or parsing raw blockchain data. The agent reads structured JSON payloads, validating ownership and balance requirements in a single step during multi-agent handoffs.

Session Control via OpenAI Agents SDK

The `revoke_session` tool terminates active Web3 authentication sessions when your OpenAI Agents SDK detects suspicious behavior through this MCP Server. If an agent identifies unusual transaction patterns, it calls this tool to secure the account immediately. This integration turns your security policies into active code using the MCP standard. The agent acts as an automated warden, keeping your Web3 app safe by purging compromised sessions without waiting for human intervention.

Setup guide

Set up Dynamic (Web3 Auth) 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 Dynamic (Web3 Auth) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Dynamic (Web3 Auth) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Dynamic (Web3 Auth) 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="Dynamic (Web3 Auth) Agent",
            instructions="You have access to Dynamic (Web3 Auth) 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 Dynamic. 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 Dynamic (Web3 Auth) 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 Dynamic (Web3 Auth) MCP in OpenAI Agents SDK

Install the package, initialize `MCPServerStreamableHttp` with your Vinkius endpoint, and register it in the `mcp_servers` list of your Agent constructor. Setting `cacheToolsList=True` ensures your agent discovers the tools without extra network roundtrips.

Yes, your routing agent can call `get_token_balances` and use the returned profile to hand off the conversation to a specialized premium agent if the wallet meets your threshold. This keeps your logic modular and secure.

Yes, you can program your agent to trigger `revoke_session` based on custom safety guardrails in your Python code. This allows the OpenAI Agents SDK to actively kick out compromised users.

Use the `get_webhooks` and `get_event_types` tools to query your active endpoints. Your agent can read these configurations directly to verify that your Web3 auth events are routing to the correct backend handlers.

This integration processes Web3 wallet addresses, profile metadata, and session tokens within an isolated V8 sandbox on Vinkius before they reach your OpenAI Agents SDK runtime. No plain-text keys are stored, and all outbound calls to Dynamic are encrypted, keeping your users' financial identities private during agent execution.

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