How to Use the Structured MCP in Pydantic AI

Q: How does Pydantic AI list structured plans?

You invoke listplans. The resulting list is validated against a Pydantic schema, meaning your agent receives predictable data structures every single time.

Q: Can I manage user profiles with pydantic-ai?

Yes. Calling getuserprofile retrieves the user details. Crucially, Pydantic ensures that this returned profile object matches the expected data model before your agent uses it.

Q: Which tools ensure data quality when using pydantic-ai?

All write operations—like createtask and updatetask—are type-safe. This gives you confidence that the structured data written back is always correct.

Q: How do I ensure a reliable workflow with Structured using pydantic-ai?

Start by listing all tasks (listtasks) to see what exists, and then use gettaskdetails for specific context. The validation layer makes this entire process highly dependable.

Use Pydantic AI to guarantee Structured data integrity and type safety when building your agent system.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Structured MCP to Pydantic AI

Create your Vinkius account to connect Structured to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Structured with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validated Task Creation

When you call `create_task`, Pydantic ensures the response is perfectly typed. If the API returns a malformed record, your agent doesn't proceed with garbage data—it fails loudly with a specific validation error. This means every time you use the tool, you get guaranteed correctness in your task records and can trust the inputs feeding into your downstream logic.

Reviewing All Structured Plans

Use `list_plans` to pull all available plans. Because of Pydantic validation, you know exactly what fields are present in every plan object returned by the MCP Server. There's no risk of missing or misspelled keys. Similarly, when fetching specific data using `get_plan_details`, the type system guarantees that the resulting JSON adheres to your defined model.

Handling Task Updates and Deletions

Updating tasks via `update_task` is safe. Pydantic validates the payload against the expected schema, so you can't accidentally send a string when an integer was required. The same safety net applies to task deletion (`delete_task`). You know exactly what data types are involved in confirming that irreversible action.

Setup guide

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

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

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

You invoke `list_plans`. The resulting list is validated against a Pydantic schema, meaning your agent receives predictable data structures every single time.

Yes. Calling `get_user_profile` retrieves the user details. Crucially, Pydantic ensures that this returned profile object matches the expected data model before your agent uses it.

All write operations—like `create_task` and `update_task`—are type-safe. This gives you confidence that the structured data written back is always correct.

Start by listing all tasks (`list_tasks`) to see what exists, and then use `get_task_details` for specific context. The validation layer makes this entire process highly dependable.

This server touches user profile data. Always ensure that any call to `get_user_profile` is handled by a model that explicitly validates and sanitizes the returned personal identifiers.

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