How to Use the DeskTime MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK delete DeskTime projects?

Yes, if you allow it. The agent can call removeproject to clean up old records. Use the SDK's built-in guardrails if you want to restrict this action.

Connect DeskTime to the OpenAI Agents SDK to build production-grade time tracking agents with built-in guardrails and handoffs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeskTime MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate DeskTime Projects with OpenAI Agents

Your OpenAI agent can manage the entire project lifecycle directly through the MCP Server. When a new client signs on, the agent triggers `create_project` and immediately populates it using `create_new_task`. You skip the manual data entry entirely. Handoffs make this powerful. A specialized billing agent can pull `get_project_details` and `list_project_tasks`, verify what is finished via `mark_task_completed`, and pass the exact billable hours to your invoicing system. Tracing in the OpenAI dashboard shows exactly which tools fired.

Track Staff Productivity

Shift the burden of checking timesheets to your agent. By calling `list_online_staff`, the system knows exactly who is logged in right now. It pulls daily stats using `get_employee_performance` to catch unusual drops in activity before the week ends. Guardrails prevent abuse here. You configure the OpenAI Agents SDK to only allow read access for these specific MCP tools. The agent reads `get_productivity_reports` to summarize company-wide trends, but safety constraints stop it from executing destructive actions.

Sync Company Data Securely

Large organizations need accurate rosters. The agent runs `list_employees` to audit the current DeskTime directory against your HR database. If someone leaves, it identifies the mismatch immediately. It fetches broader context via `get_company_info` to ensure reporting aligns with corporate settings. Because the SDK auto-discovers these endpoints, you just pass the server URL to the constructor and the agent handles the rest.

Setup guide

Set up DeskTime 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 DeskTime tools at runtime.
3

Create your Agent

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

Run the agent

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

Initialize MCPServerStreamableHttp with your Vinkius URL. Pass it to your agent constructor in the mcp_servers array. Set cacheToolsList=True to speed up tool discovery.

Yes, if you allow it. The agent can call `remove_project` to clean up old records. Use the SDK's built-in guardrails if you want to restrict this action.

The server provides the tools, while the SDK manages the handoffs. One agent can run `list_project_tasks`, then transfer the resulting task list to a specialized reporting agent.

Prompt your agent to check current staffing. It automatically maps that request to the `list_online_staff` tool. The response feeds directly into your OpenAI trace logs.

The server handles sensitive employee time logs and productivity scores. Vinkius isolates this execution in an ephemeral V8 sandbox. Your agent only accesses the exact metrics required for the specific prompt, leaving zero residual data behind.

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