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 Pydantic AI 17 tools — connect in under 2 minutes

Name: Teamwork Projects
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 17 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Teamwork Projects through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

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 pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

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

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Teamwork Projects "
            "(17 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Teamwork Projects?"
    )
    print(result.data)

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.

Pydantic AI validates every Teamwork Projects tool response against typed schemas, catching data inconsistencies at build time. Connect 17 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

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 Pydantic AI 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 Pydantic AI via MCP

Follow these steps to integrate the Teamwork Projects MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 17 tools from Teamwork Projects with type-safe schemas

Why Use Pydantic AI with the Teamwork Projects MCP Server

Pydantic AI provides unique advantages when paired with Teamwork Projects through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Teamwork Projects integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Teamwork Projects connection logic from agent behavior for testable, maintainable code

Teamwork Projects + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Teamwork Projects MCP Server delivers measurable value.

Type-safe data pipelines: query Teamwork Projects with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Teamwork Projects tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Teamwork Projects and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Teamwork Projects responses and write comprehensive agent tests

Teamwork Projects MCP Tools for Pydantic AI (17)

These 17 tools become available when you connect Teamwork Projects to Pydantic AI 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 Pydantic AI

Ready-to-use prompts you can give your Pydantic AI 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 Pydantic AI

Common issues when connecting Teamwork Projects to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Teamwork Projects + Pydantic AI FAQ

Common questions about integrating Teamwork Projects MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Teamwork Projects MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.