How to Use the Worktile MCP in Pydantic AI

Q: How do I ensure task status is correct with Worktile and Pydantic AI?

Use listtaskstates to get a definitive, structured list of all possible statuses. Your agent can then use this knowledge when calling updatetask to maintain data integrity within the work tile system.

Q: What specific project details does Worktile and Pydantic AI handle?

The server retrieves project metadata through getproject, which includes task lists (listtasks) and overall team context. The entire payload is validated, preventing data corruption.

Q: Can I track all activity across multiple projects using Worktile and Pydantic AI?

Yes. You start by listing all available work tiles (listprojects) and then iterate over those results, calling getproject for each one. The type safety ensures that every piece of data you collect is clean.

Type-Safe Workflows: Manage Worktile tasks using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Worktile MCP to Pydantic AI

Create your Vinkius account to connect Worktile to Pydantic AI 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 Worktile with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Task Management with the MCP Server

The `create_task` tool lets your agent create a new record in Worktile, forcing the input data to match expected schemas. You can then use `list_tasks` to pull back those tasks and validate their structure. If you need to adjust an existing ticket, the `update_task` function is available. Because of Pydantic validation, the agent will fail loudly if the API returns unexpected fields.

Project Information via Pydantic AI

`list_projects` provides a strictly typed list of all Worktile projects. Need more depth? `get_project` pulls detailed information, and every field it receives is validated against your defined models. It also lets you get organizational context using `get_team_info`, ensuring the team data structure remains consistent.

Team Coordination with MCP Server

To communicate, use `send_message` to send content to a specific channel. Before that, your agent should list channels using `list_channels`. This whole process is type-checked from start to finish. Furthermore, you can get the user roster by calling `list_members`, guaranteeing that the member data matches your expected Python class structure.

Setup guide

Set up Worktile MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "worktile-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Worktile tools.",
)

result = await agent.run("List recent Worktile transactions")
print(result.output)

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 Worktile. 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 Worktile 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 Worktile MCP in Pydantic AI

Use `list_task_states` to get a definitive, structured list of all possible statuses. Your agent can then use this knowledge when calling `update_task` to maintain data integrity within the work tile system.

The server retrieves project metadata through `get_project`, which includes task lists (`list_tasks`) and overall team context. The entire payload is validated, preventing data corruption.

You'll never get silent failures or corrupted data. If the underlying API sends unexpected information, your agent fails with a clear validation error, letting you know exactly where the contract was broken.

Yes. You start by listing all available work tiles (`list_projects`) and then iterate over those results, calling `get_project` for each one. The type safety ensures that every piece of data you collect is clean.

The system manages project details, task records, team member profiles, and message channels. All data points are strictly modeled so your agent can trust the structure of every response.

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