How to Use the timeghost MCP in OpenAI Agents SDK

Connect your OpenAI Agent to timeghost. Build autonomous agents that manage projects and track time with built-in safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect timeghost MCP to OpenAI Agents SDK

Create your Vinkius account to connect timeghost to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup timeghost with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate Project Scoping

Stop digging through web portals for project details. You can build an agent that finds a project ID with `list_timeghost_projects`, pulls its full record using `get_timeghost_project`, and then lists all associated work items with `list_timeghost_tasks`. This is how you build specialized agents that hand off work. One agent finds the project, another analyzes the tasks. The OpenAI Agents SDK makes these handoffs simple, so your agents can collaborate on complex jobs without you writing glue code.

Manage Workspace Access with this MCP Server

Give your agent the ability to understand your team structure. It can get a full list of available environments using `list_timeghost_workspaces` to orient itself. From there, a separate, more privileged agent could use `list_timeghost_members` to check who has access to what. This is perfect for building automated onboarding bots or running security checks, all within the safety of the agent framework.

Build Auditable Time Reports

This MCP server is your agent's direct line to billing data. Before running a report, your agent can ping the API with `check_timeghost_status` to make sure it's online. Then, it can find the right customer with `list_timeghost_clients` and pull all their hours using `list_timeghost_entries`. Need to investigate a specific line item? The agent can use the ID from the list to fetch a single record with `get_timeghost_entry`. Because every action is traced in your OpenAI dashboard, you have a full audit log of how the report was generated.

Setup guide

Set up timeghost 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 timeghost tools at runtime.
3

Create your Agent

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

Run the agent

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

It's automatic. Just pass the MCP server endpoint to the Agent constructor. The SDK's discovery mechanism reads the tool manifest and makes them available to the agent with no extra code needed.

No, this server is read-only. It's designed for agents that need to analyze, report on, and audit existing timeghost data, not create or modify it. You'll use tools like `list_timeghost_entries` and `get_timeghost_project`.

Guardrails and tracing. The SDK lets you define safety rules and provides a full trace of the agent's actions. This is critical for production systems that handle sensitive billing data from timeghost.

Yes. You can equip one specialized agent with these tools, and it can hand off results to other agents. For example, a 'reporting' agent could use timeghost tools and pass the data to a 'summarization' agent.

This server only reads data; it never writes. Your Vinkius token secures the connection, and the server itself is ephemeral. The agent can only access the time entries, project details, and client names that your timeghost API key permits.

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