How to Use the Deel MCP in OpenAI Agents SDK

Q: How do I configure the Deel MCP Server inside my OpenAI Agents SDK pipeline?

Install the SDK via pip and initialize the server using MCPServerStreamableHttp with your Vinkius endpoint. Pass the server instance directly to your agent constructor. Setting cacheToolsList=True keeps your tool discovery fast.

Q: How does the OpenAI Agents SDK handle tracing for Deel financial queries?

Every call to tools like listpayments or listinvoices goes through the OpenAI dashboard. You get a complete execution log of what your agent requested and what the platform returned.

Q: Can my agent update milestone statuses?

No. The listtasks and listmilestones tools are read-only. Your agent can read the current status and flag overdue tasks, but it cannot write changes back to the platform.

Q: How is my team's Deel payment history protected when using this MCP integration?

Your payment history data, accessed via listpayments, never touches public logs. Vinkius runs the server in an ephemeral, zero-trust sandbox. The SDK routes these queries securely through your private endpoint token, preventing unauthorized eyes from seeing your disbursement amounts.

Run safe, production-grade Deel operations with OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deel MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pull contract terms directly into your OpenAI Agents SDK

The `get_contract` tool fetches active terms, compliance rules, and rates directly into your OpenAI agent context. Your agent parses this data to verify compliance before processing payments or updating records. Using the `list_contracts` tool, your agents scan through active agreements to flag expiring agreements. This execution loop feeds clean data straight into your tracing dashboard using this MCP Server safely.

Track team expenses and invoices with built-in guardrails

The `list_expenses` tool exposes receipt metadata and approval states to your agent. This lets you build verification agents that cross-reference submitted receipts against existing company policies. By combining this with `list_invoices`, your agent handles billing checks without human intervention. You get accurate books because the SDK ensures these financial actions run through strict validation checks before execution. This MCP Server handles the heavy lifting.

Coordinate global team schedules using this MCP Server

The `list_time_off` tool gives your agent instant access to leave requests and approval statuses. This allows your team-coordination agents to schedule projects around real-world availability. Pairing this with `list_people` lets you map out team locations and roles. It makes resource planning straightforward because your agent knows exactly who is online and where they work.

Setup guide

Set up Deel 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 Deel tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK via pip and initialize the server using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass the server instance directly to your agent constructor. Setting `cacheToolsList=True` keeps your tool discovery fast.

Yes. You control tool exposure at the agent constructor level. If you only want an agent to read schedules, only pass it the specific tools like `list_time_off` and `list_people`.

Every call to tools like `list_payments` or `list_invoices` goes through the OpenAI dashboard. You get a complete execution log of what your agent requested and what the platform returned.

No. The `list_tasks` and `list_milestones` tools are read-only. Your agent can read the current status and flag overdue tasks, but it cannot write changes back to the platform.

Your payment history data, accessed via `list_payments`, never touches public logs. Vinkius runs the server in an ephemeral, zero-trust sandbox. The SDK routes these queries securely through your private endpoint token, preventing unauthorized eyes from seeing your disbursement amounts.

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