How to Use the Fieldly MCP in Pydantic AI

Q: How do I set up the Fieldly MCP Server with Pydantic AI?

Install pydantic-ai-slimmcp, import MCPToolset with your Vinkius HTTP URL, and pass the toolset instance into your Agent constructor. This exposes all construction tools with strict runtime validation.

Q: Can I use Pydantic AI to validate Fieldly work item creation?

Yes. When the agent calls createworkitem, Pydantic AI ensures the input parameters match the expected schema before the payload ever leaves your application.

Q: How does Pydantic AI secure my customer contact lists?

Customer details fetched via listcustomers are validated locally in your runtime memory. The Vinkius sandbox ensures that no PII is stored permanently, maintaining strict compliance with your data policies.

Build type-safe construction agents using Pydantic AI and the Fieldly MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fieldly MCP to Pydantic AI

Create your Vinkius account to connect Fieldly 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 Fieldly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Runtime Validation for Construction ERP

Let's face it: construction data cannot tolerate silent errors. Pydantic AI guarantees that every payload returned by the Fieldly MCP Server matches your exact schema, failing loudly if `get_invoice` returns a malformed string or an unexpected null value. If the API structure changes, your agent throws a validation error immediately instead of processing a corrupt invoice. This protects your accounting system from bad data when running automated checks against `list_invoices`.

Strict Type Checks on MCP Server Work Items

When your agent schedules new tasks, type safety keeps the system stable. Pydantic AI validates the arguments for `create_work_item` before sending the request, ensuring that dates, user IDs, and descriptions conform to strict Python types. If the model attempts to pass a non-integer ID to `get_booking` or a missing field to `get_work_item`, the framework blocks the call at the boundary. This saves your API quota and prevents database corruption.

Model-Agnostic Validation

Run your field operations on any LLM while keeping your data validation intact. Whether you plug in Anthropic, OpenAI, or a local model, Pydantic AI enforces consistent schemas across all 11 tools, from `list_customers` to `list_articles`. This decoupling means you can swap the underlying model to optimize for speed or cost without rewriting your integrations. The agent will still reliably parse `list_users` and output clean, validated records every time.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`, import `MCPToolset` with your Vinkius HTTP URL, and pass the toolset instance into your `Agent` constructor. This exposes all construction tools with strict runtime validation.

The framework raises a validation error immediately. This prevents your agent from parsing corrupted structures when querying tools like `get_work_item` or `list_bookings`.

Yes. When the agent calls `create_work_item`, Pydantic AI ensures the input parameters match the expected schema before the payload ever leaves your application.

Yes, Pydantic AI natively supports async Python, allowing your agent to query `list_articles` and `list_users` concurrently without blocking your main application loop.

Customer details fetched via `list_customers` are validated locally in your runtime memory. The Vinkius sandbox ensures that no PII is stored permanently, maintaining strict compliance with your data policies.

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