How to Use the DPD MCP in Pydantic AI

Q: How do I connect the DPD MCP Server to Pydantic AI?

Use the unified MCPToolset constructor with your Vinkius HTTP endpoint and pass it to your Agent. This exposes all ten validated logistics tools to your model.

Q: Can Pydantic AI filter historical DPD shipments?

Yes, the agent calls listshipments with a filtered JSON payload to extract specific orders. The returned list of shipments is automatically validated against your Pydantic schemas.

Q: How does Pydantic AI handle DPD parcel cancellations?

Your agent executes cancelshipment to void active tracking numbers in real-time. The response is parsed instantly to confirm the cancellation succeeded.

Q: Does the DPD integration support finding local parcel shops?

The agent calls findparcelshop to locate nearby pickup points based on geographical inputs. This returns structured, type-safe location data for your user interface.

Run type-safe DPD logistics workflows in Pydantic AI with runtime validation for every shipment tool.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DPD MCP to Pydantic AI

Create your Vinkius account to connect DPD 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 DPD with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate verified DPD labels using Pydantic AI.

`create_shipment` guarantees that your shipping payloads match the strict schemas expected by DPD. Pydantic AI validates the return values instantly, catching structural errors before you waste money on invalid bookings. Once validated, the system calls `get_labels` to download the printable PDF assets. This strict validation prevents corrupt label files from reaching your warehouse packing stations.

Audit DPD tracking data.

`get_parcel_status` returns structured tracking histories that are validated against native Python models. If the DPD API changes its payload format, your application fails loudly instead of processing corrupt data. To audit entire batches, your MCP agent invokes `get_shipment_status` to parse the complete routing history. This keeps your internal databases perfectly synchronized with the physical courier network.

Query DPD products safely.

`list_products` returns a verified list of shipping services that your agent can safely parse. This prevents your booking logic from selecting deprecated or unavailable shipping tiers. When closing out physical shipments, the agent calls `get_manifest` to compile the official handoff documentation. Every field in the resulting manifest is validated to ensure compliance with courier standards.

Setup guide

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

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

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

Use the unified `MCPToolset` constructor with your Vinkius HTTP endpoint and pass it to your Agent. This exposes all ten validated logistics tools to your model.

Yes, the agent calls `list_shipments` with a filtered JSON payload to extract specific orders. The returned list of shipments is automatically validated against your Pydantic schemas.

Your agent executes `cancel_shipment` to void active tracking numbers in real-time. The response is parsed instantly to confirm the cancellation succeeded.

The agent calls `find_parcelshop` to locate nearby pickup points based on geographical inputs. This returns structured, type-safe location data for your user interface.

Vinkius handles your recipient addresses and parcel details inside a secure, ephemeral V8 isolate. No personal shipping data is stored or logged, keeping your logistics pipeline compliant.

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