How to Use the LiftedWork MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK system write tasks using LiftedWork?

Yes. Your agent can use createtask by passing a structured JSON string containing the task details. The SDK handles the schema validation, ensuring the agency task list stays clean.

Run production-grade hiring workflows and track job applications using this MCP Server in your OpenAI Agents SDK pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiftedWork MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate job setup with OpenAI Agents SDK

The `create_project` tool lets your agent spin up fresh client engagements the second a job seeker matches an opening. This MCP tool lets your Python pipeline call this endpoint to establish the workspace structure without manual data entry. Once the workspace is live, the agent passes structured JSON payloads to `create_task` to map out the interview milestones. You get clean, predictable task creation that keeps recruiters and candidates on the exact same page.

Pull client and project directories on demand

The `list_clients` tool pulls up your complete partner directory so your agent can check hiring companies before matching candidates. It gives your system immediate access to active accounts without leaving the Python execution loop. Pairing that with `list_projects` lets your agent see where active openings are and which teams have budget. This keeps your matching engine grounded in real-world demand instead of stale database dumps.

Audit agency velocity and time logs

The `list_tasks` tool shows you every active assignment across your pipeline so your agent can flag bottlenecks. It feeds raw task states directly into your OpenAI dashboard tracing, showing you exactly where candidates stall. To keep billing accurate, the `list_time_entries` tool pulls logged hours for contract placements. Your agent can audit these hours weekly to catch billing errors before invoices go out.

Setup guide

Set up LiftedWork 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 LiftedWork tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package and use MCPServerStreamableHttp to point to the host. Pass the server instance directly to your agent constructor, and the system automatically registers all six tools.

Yes. Your agent can use `create_task` by passing a structured JSON string containing the task details. The SDK handles the schema validation, ensuring the agency task list stays clean.

The server handles connection pooling and rate limits at the gateway layer. Your Python agent can safely query `list_time_entries` or `list_projects` without hitting performance bottlenecks.

You can design specialized agents where one handles client discovery using `list_clients` and another manages tasks. The SDK handles the state handoff while sharing the same server connection.

All recruitment data, client records, and time logs remain isolated in V8 sandboxes. The server only exposes read-write access to the specific database tables you authorize, meaning candidate resumes and hourly rates never leak to public models.

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