How to Use the Argyle MCP in OpenAI Agents SDK

Q: How do I connect Argyle to the OpenAI Agents SDK?

Install openai-agents via pip. Initialize MCPServerStreamableHttp with your Vinkius URL and pass it to your Agent constructor. The framework handles the rest.

Q: Can OpenAI Agents SDK cache the Argyle tool definitions?

Yes. Set cacheToolsList=True when configuring the server. This prevents the agent from fetching the schema on every run, saving latency.

Build production HR agents with OpenAI Agents SDK to verify employment and income data via 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 Argyle MCP to OpenAI Agents SDK

Create your Vinkius account to connect Argyle 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 Argyle with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

OpenAI Agents SDK Auto-Discovers Argyle

The `list_users` and `create_user` tools let your agent manage the entire Argyle onboarding flow without manual intervention. You just pass the Vinkius endpoint token into the `MCPServerStreamableHttp` constructor. OpenAI's framework automatically reads the tool schemas and registers them for your agent. Handoffs become trivial when you build specialized HR agents. One agent handles onboarding while another uses the `get_account_check` tool to verify connection status before passing control. Setting `cacheToolsList=True` keeps these transitions fast during production workloads.

Guardrailed Income Verification

Pulling sensitive salary data requires strict safety boundaries, which is why your agent uses the `get_income` and `list_payouts` tools under OpenAI's built-in guardrails. Before any payout data hits your database, the MCP protocol validates the action. You trace the exact sequence of API calls right in the OpenAI dashboard. Building this from scratch takes weeks of error handling. Now your agent just calls the tools asynchronously while the SDK manages the context window. It pulls individual pay period details and aggregates them safely.

Tracing Employment History

The `get_employment` tool returns a user's entire work history directly into your agent's context. Your system evaluates tenure and employer details against your business logic. When you deploy this MCP Server, Vinkius handles the underlying authentication so your Python code stays clean. Tracking identity verified by third parties happens through the `list_identities` tool. Your OpenAI agent cross-references this PII with internal records. Everything runs through the V8 Isolate Sandbox for guaranteed isolation.

Setup guide

Set up Argyle 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 Argyle tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip. Initialize `MCPServerStreamableHttp` with your Vinkius URL and pass it to your Agent constructor. The framework handles the rest.

Yes. Set `cacheToolsList=True` when configuring the server. This prevents the agent from fetching the schema on every run, saving latency.

The SDK's async context manager processes requests efficiently. If an agent spams the `list_payouts` tool, Vinkius intercepts it at the sandbox level before it hits the provider.

No. Auto-discovery is built into the MCP standard. Your agent immediately knows how to verify employment or check account statuses.

Extremely secure. Vinkius runs the connection in an ephemeral V8 Isolate Sandbox. Your users' pay stubs, W-2 totals, and verified identities pass directly to your agent without touching our disks.

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