How to Use the Arrivy MCP in Pydantic AI

Q: How do I register the Arrivy MCP Server in a Pydantic AI agent?

Initialize MCPToolset with the Vinkius HTTP endpoint. Then, pass that toolset instance directly into the toolsets argument of your Pydantic AI Agent.

Q: Does Pydantic AI support the deprecated MCPServerHTTP for Arrivy?

No. You must use the unified MCPToolset class which supports both Streamable HTTP and SSE transports for your connections.

Execute type-safe field service scheduling and dispatch workflows using Pydantic AI with validated MCP endpoints.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arrivy MCP to Pydantic AI

Create your Vinkius account to connect Arrivy 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 Arrivy with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe customer creation and verification

`create_customer` enforces strict type checking on all customer records created by your Pydantic AI agent. If your agent tries to supply an invalid phone number format, Pydantic AI rejects it instantly at runtime. This guarantees that only clean, validated payloads hit the Arrivy MCP Server, preventing silent failures in your field operations database. You get absolute data integrity out of the box.

Type-Safe Task Management via Pydantic AI MCP Server

`create_task` ensures that every field service ticket generated by your model adheres to your exact schema. The Pydantic AI framework validates the response from the server against strict Python models. If the model hallucinates a field or returns unexpected JSON, the toolset raises a clear validation error, stopping the bad data in its tracks. This keeps your field dispatch system completely reliable.

Verifying connection integrity on startup

`get_account_check` verifies that your Arrivy credentials are valid before your agent starts executing workflows. Running this check on startup prevents your type-safe agent from failing mid-run due to an expired token. By integrating this check into your initialization logic, you ensure your production runtime has a clear connection to the Vinkius MCP endpoint. This reduces runtime surprises during field operations.

Setup guide

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

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

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

Initialize `MCPToolset` with the Vinkius HTTP endpoint. Then, pass that toolset instance directly into the `toolsets` argument of your Pydantic AI `Agent`.

No. You must use the unified `MCPToolset` class which supports both Streamable HTTP and SSE transports for your connections.

The framework validates all incoming tool data at runtime. If the payload doesn't match the expected type schema, Pydantic AI raises a validation error instead of passing bad data to your model.

Yes. Because Pydantic AI is model-agnostic, you can connect your local Ollama or Llama model to the Arrivy MCP toolset as easily as you would with OpenAI.

Your sensitive customer names and dispatch addresses are processed in memory through the type-safe Python runtime. The Vinkius sandbox acts as a secure, ephemeral bridge, never caching or storing your field 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