How to Use the Tower MCP in Pydantic AI

Q: Can I use Pydantic AI to manage tasks in Tower?

Yes. You can call createtask, listtasks, and updatetask. Every time you interact with a task record, the framework validates the input and output for type safety.

Q: What kind of data does Pydantic AI touch regarding discussions?

It touches the structured output from listdiscussions. This includes listable items like discussion titles, dates, and associated project IDs, all validated against your models.

Guaranteed correctness when using the Pydantic AI framework with Tower tasks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tower MCP to Pydantic AI

Create your Vinkius account to connect Tower 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 Tower with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Updating Task Statuses with MCP Server

Changing a task's status shouldn't result in garbage data. When your agent calls `update_task`, the Pydantic AI framework validates every field against a strict schema. If Tower sends bad data, you fail loudly. This guarantees that the new state of the task record is correct before it ever hits your application layer.

Listing Projects and Teams with Pydantic AI

Need to build a report listing all projects or all teams? Your agent uses `list_projects` or `list_teams`. Because of the Pydantic validation, you're guaranteed that the returned JSON structure matches your expected Python models. No more guessing what fields are available. The data is predictable.

Retrieving Detailed Project Information

Getting project details with `get_project` is simple, but getting it *right* is hard. Pydantic AI forces validation on the returned object, meaning you'll get exactly what you asked for—no unexpected fields or null values. This level of correctness makes your agent reliable in production environments where data integrity matters most.

Setup guide

Set up Tower 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": {
        "tower-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Tower 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 Tower. 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 Tower 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 Tower MCP in Pydantic AI

It validates the entire output payload from the MCP Server against defined Python models. If any part of the project data fails validation, the agent throws an explicit error instead of silently using bad information.

Yes. You can call `create_task`, `list_tasks`, and `update_task`. Every time you interact with a task record, the framework validates the input and output for type safety.

It handles structured records across all tools, including project details (`get_project`), member lists (`list_members`), and document folder paths. Everything is typed.

It validates every step of a multi-step process. Whether you're listing projects, then checking tasks, and finally updating one, each returned object is type-checked.

It touches the structured output from `list_discussions`. This includes listable items like discussion titles, dates, and associated project IDs, all validated against your models.

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