How do I get my Teamwork Access Token?

Log in to Teamwork, go to your Profile picture > My Profile > Developer, and generate a Personal Access Token.

Can I create tasks with assignees?

Yes! Use the create_task action with a JSON body that includes content, tasklist_id, and responsible-party-ids for assignment.

Can I log time against a project?

Yes! Use the create_time_entry action with a JSON body that includes description, duration (in minutes or seconds), and date.

Can I retrieve project milestones?

Yes! Use the list_milestones action to get all project milestones and their deadlines.

Teamwork Projects MCP Server for OpenAI Agents SDK 17 tools — connect in under 2 minutes

Name: Teamwork Projects
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 17 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Teamwork Projects 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="Teamwork Projects Assistant",
            instructions=(
                "You help users interact with Teamwork Projects. "
                "You have access to 17 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Teamwork Projects"
        )
        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 Teamwork Projects MCP Server

Connect Teamwork to any AI agent and manage your project delivery platform — create and track tasks, manage milestones, log time, post messages, and monitor project progress through natural conversation.

The OpenAI Agents SDK auto-discovers all 17 tools from Teamwork Projects through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Teamwork Projects, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Project Management — List and create projects for organizing work
Task Management — Create, update, and delete tasks with assignees and due dates
Milestones — Track project milestones and deadlines
Time Tracking — Log and review time entries against projects
Messages — Post announcements and discussions in projects
Files — List and access project files and attachments

The Teamwork Projects MCP Server exposes 17 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 Teamwork Projects to OpenAI Agents SDK via MCP

Follow these steps to integrate the Teamwork Projects 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 17 tools from Teamwork Projects

Why Use OpenAI Agents SDK with the Teamwork Projects MCP Server

OpenAI Agents SDK provides unique advantages when paired with Teamwork Projects 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

Teamwork Projects + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Teamwork Projects MCP Server delivers measurable value.

Automated workflows: build agents that query Teamwork Projects, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Teamwork Projects, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Teamwork Projects tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Teamwork Projects to resolve tickets, look up records, and update statuses without human intervention

Teamwork Projects MCP Tools for OpenAI Agents SDK (17)

These 17 tools become available when you connect Teamwork Projects to OpenAI Agents SDK via MCP:

create_message

Body should include title and body content. Post a new message in a project

create_milestone

Body should include title and deadline date. Create a new milestone in a project

create_project

Body should include name and optional settings. Create a new project

create_task

Body should include content, tasklist_id, assignee_ids, and due dates. Create a new task

create_time_entry

Body should include description, duration, and date. Log a new time entry

delete_task

Delete a task

get_current_user

Use this to verify connection and identify your user ID. Get the authenticated user profile

get_project

Get details of a specific project

get_task

Get details of a specific task

list_files

List all files in a project

list_messages

List all messages in a project

list_milestones

List all milestones in a project

list_projects

Use project IDs to query tasks, milestones, and other resources within specific projects. List all projects accessible to the user

list_tasklists

Use task list IDs to query specific tasks. List all task lists in a project

list_tasks

List all tasks in a project

list_time_entries

List all time entries in a project

update_task

Update an existing task

Example Prompts for Teamwork Projects in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Teamwork Projects immediately.

"Show me all my projects."

"List all tasks in project 12345."

"Create a milestone 'Phase 1 Complete' with deadline 2025-05-01 in project 12345."

Troubleshooting Teamwork Projects MCP Server with OpenAI Agents SDK

Common issues when connecting Teamwork Projects 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.

Teamwork Projects + OpenAI Agents SDK FAQ

Common questions about integrating Teamwork Projects 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.