How do I get an Everhour API Key?

Log in to your Everhour account, navigate to your user profile settings (top right), and click on **API**. You can find or generate your unique API Key there.

Can the agent start a new timer?

This integration currently focuses on listing and auditing projects, tasks, and time entries. Starting or stopping live timers should be performed via the Everhour browser extension or mobile app.

Does the integration show real-time budget usage?

Yes, you can use the list_projects_within_budget tool to retrieve current budget utilization rates and identify projects that are approaching their limits.

Everhour Time Tracking MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Everhour Time Tracking
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Everhour Time Tracking through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Everhour Time Tracking Assistant",
            instructions=(
                "You help users interact with Everhour Time Tracking. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Everhour Time Tracking"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Everhour Time Tracking MCP Server

Integrate Everhour, the powerful time tracking and project management software, directly into your AI workflow. Manage your projects and tasks, track real-time time entries and team productivity, monitor project budgets and billing status, and oversee your entire team's workload using natural language.

The OpenAI Agents SDK auto-discovers all 10 tools from Everhour Time Tracking through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Everhour Time Tracking, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Project Oversight — List and retrieve detailed information, budgets, and status for all your tracked projects.
Time Intelligence — Monitor team time records, resolving task IDs, durations, and active user timers in real-time.
Budget Management — Access and monitor project budgets, identifying utilization rates and identifying projects at risk of exceeding limits.
Productivity Auditing — Retrieve high-level summaries of recent time entries, task completion, and organizational account health instantly.

The Everhour Time Tracking MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Everhour Time Tracking to OpenAI Agents SDK via MCP

Follow these steps to integrate the Everhour Time Tracking MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Everhour Time Tracking

Why Use OpenAI Agents SDK with the Everhour Time Tracking MCP Server

OpenAI Agents SDK provides unique advantages when paired with Everhour Time Tracking through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Everhour Time Tracking + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Everhour Time Tracking MCP Server delivers measurable value.

Automated workflows: build agents that query Everhour Time Tracking, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Everhour Time Tracking, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Everhour Time Tracking tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Everhour Time Tracking to resolve tickets, look up records, and update statuses without human intervention

Everhour Time Tracking MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Everhour Time Tracking to OpenAI Agents SDK via MCP:

get_currently_running_timer

Retrieve the task and start time for any currently active timer

get_everhour_user_metadata

Retrieve metadata and profile information for the current Everhour user

get_project_detailed_data

Get detailed settings and budget information for a specific project

list_billing_clients

List all clients configured for project billing and invoicing

list_organization_team_members

List all team members and their roles in the organization

list_project_tasks

List all tasks within a specific project

list_projects_within_budget

Identify projects that are currently within their assigned time or monetary budget

list_team_time_records

List time records for the team within a specific date range

list_tracked_projects

List all projects managed in your Everhour account

quick_time_tracking_audit

Retrieve a high-level summary of recent time entries and active projects

Example Prompts for Everhour Time Tracking in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Everhour Time Tracking immediately.

"List all projects currently over budget."

"Show me the tasks for project 'Mobile App'."

"What is the team productivity summary for this week?"

Troubleshooting Everhour Time Tracking MCP Server with OpenAI Agents SDK

Common issues when connecting Everhour Time Tracking to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Everhour Time Tracking + OpenAI Agents SDK FAQ

Common questions about integrating Everhour Time Tracking MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.