How to Use the Giddyup MCP in Pydantic AI

Q: How do I register the Giddyup toolset in Pydantic AI?

Use the MCPToolset constructor with your Vinkius HTTP endpoint. This registers all 13 tools, including createlead and getjob, directly to your agent.

Q: How is my Giddyup technician and dispatch data secured?

Technician records retrieved via listusers and job details from getjob are processed inside isolated V8 sandboxes. Vinkius handles these requests ephemerally and never stores your operational data.

Run type-safe Giddyup construction dispatches using Pydantic AI runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Giddyup MCP to Pydantic AI

Create your Vinkius account to connect Giddyup 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 Giddyup with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe job dispatching with Pydantic AI

The `create_job` tool enforces strict Pydantic AI validation on every Giddyup dispatch request before execution. When your agent attempts to schedule a technician, the framework verifies the payload against Python models at runtime. It stops bad data before it ever hits the field. If your model generates an invalid date for `update_job`, Pydantic AI halts the Giddyup dispatch immediately. You get a loud, clear validation error instead of a silent database corruption. It ensures your technicians always get clean, actionable instructions.

Reliable lead and customer tracking

The `get_customer` tool retrieves Giddyup customer profiles with guaranteed Pydantic AI type safety. Because the framework validates every incoming response, your agent can safely parse customer details without risking runtime crashes. It makes your field service integrations incredibly reliable. This prevents unexpected null values from crashing your Giddyup `update_lead` sales pipeline. Your agent can read leads using `list_leads` and write updates, confident that every field matches your local data models. It is the cleanest way to run construction sales operations.

Model-agnostic dispatch validation via MCP Server

The `list_users` tool pulls your Giddyup technician list into any Pydantic AI agent backend. Whether you use local models or commercial APIs, this MCP Server integration ensures consistent data formatting across different model providers. It gives you complete freedom to switch LLMs without rewriting dispatch logic. The server runs in a secure Vinkius sandbox, protecting your Giddyup `list_invoices` data from unauthorized model access. Your Pydantic AI agent communicates with the Giddyup API through a single secure endpoint. You don't have to manage complex authentication keys inside your codebase.

Setup guide

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

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

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

The framework will raise a validation error immediately. This protects your system from processing corrupt `list_invoices` or job data, forcing the agent to handle the error gracefully.

Use the `MCPToolset` constructor with your Vinkius HTTP endpoint. This registers all 13 tools, including `create_lead` and `get_job`, directly to your agent.

Yes, Pydantic AI requires the MCP Server to run externally. Vinkius hosts the server for you, providing a permanent HTTP endpoint for your agent to connect to.

Pass your Vinkius MCP endpoint token in the headers when initializing the toolset. This single token handles all authentication to the Giddyup API.

Technician records retrieved via `list_users` and job details from `get_job` are processed inside isolated V8 sandboxes. Vinkius handles these requests ephemerally and never stores your operational data.

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