How to Use the Moova MCP in Pydantic AI

Q: How do I integrate the Moova MCP server into a Pydantic AI project?

Install the slim package with pip install "pydantic-ai-slimmcp". Then, initialize MCPToolset with your Vinkius HTTP URL and register it in your agent's toolsets argument.

Q: How does Pydantic AI handle validation errors from Moova tools?

If a tool like getshipment returns data that violates your schemas, the framework raises a validation error. This prevents your agent from making decisions based on corrupted or hallucinated logistics data.

Q: Can I update a shipment status after the carrier has collected it?

No. While your agent can run updateshipment to modify details before pickup, changes are blocked once the carrier has collected the package.

Build type-safe logistics agents with Pydantic AI to validate shipping details, track orders, and prevent bad API payloads.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moova MCP to Pydantic AI

Create your Vinkius account to connect Moova 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 Moova with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe shipping workflows with Pydantic AI

Never worry about silent failures or malformed payloads again. By connecting this MCP Server to your Pydantic AI agent, every logistics response is validated against strict Python types at runtime. When your agent calls `create_shipment`, the framework ensures all address fields match your exact data models before hitting the carrier. If the external API returns unexpected data formats, your agent fails loudly and immediately. This strict validation prevents corrupted records from polluting your database, making it ideal for enterprise order management.

Bulletproof carrier rate validation

Ensure your pricing calculations are always accurate. Your agent can run `get_budget` to fetch live carrier rates, with Pydantic validating the numeric types of the returned pricing options. This guarantees your system never processes a null or invalid shipping quote. Before executing the shipment, the agent can check `list_coverage_zones` to verify delivery boundaries. If the destination is outside your active zones, the validation layer catches it instantly, letting your agent handle the error gracefully.

Safe webhook management and tracking

Keep your tracking systems synchronized securely via this MCP Server. The agent runs `create_webhook` to establish real-time update endpoints, ensuring the registered URLs match your expected schema. If an endpoint becomes obsolete, the agent removes it using `delete_webhook`. To handle customer support tickets, your agent retrieves shipment histories via `track_shipment` or checks the current state using `get_shipment_status`. Every status update is parsed through Pydantic, guaranteeing consistent data structures across all carriers.

Setup guide

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

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

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

Install the slim package with `pip install "pydantic-ai-slim[mcp]"`. Then, initialize `MCPToolset` with your Vinkius HTTP URL and register it in your agent's `toolsets` argument.

If a tool like `get_shipment` returns data that violates your schemas, the framework raises a validation error. This prevents your agent from making decisions based on corrupted or hallucinated logistics data.

Yes, Pydantic AI is model-agnostic. You can connect this MCP Server to your local models or commercial APIs while maintaining strict runtime validation for all logistics tools.

No. While your agent can run `update_shipment` to modify details before pickup, changes are blocked once the carrier has collected the package.

Your shipping addresses, contact details, and package dimensions are processed within isolated V8 runtimes. Vinkius secures your API tokens upstream, so your raw credentials are never exposed to the agent or LLM providers.

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