How to Use the DPD MCP in Google ADK

Q: How do I register DPD MCP tools within Google ADK?

Instantiate McpToolset with your Vinkius HTTP URL and pass it to your LlmAgent. Your Gemini model immediately gains access to all ten DPD shipping endpoints.

Q: Can Google ADK find nearby drop-off locations using DPD?

Yes, the agent calls findparcelshop with latitude and longitude coordinates. This returns a list of active physical pickup points for customer returns or drop-offs.

Q: How does Google ADK handle bulk shipment retrieval from DPD?

The agent executes listshipments with custom JSON filters to parse historical orders. You can feed this output directly into BigQuery for long-term logistics analysis.

Q: Can my agent cancel a DPD shipment?

Your agent uses cancelshipment to immediately void any labels that are no longer needed. This API call stops the fulfillment process before the courier collects the physical package.

Connect Gemini models to DPD via Google ADK to automate logistics directly from your enterprise database.

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 Google ADK

Create your Vinkius account to connect DPD to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Book DPD shipments directly from Google ADK.

`create_shipment` executes booking requests directly from your Google ADK agent using structured data from your database. The agent reads pending orders from BigQuery and formats them into JSON payloads to generate parcel numbers instantly. Once booked, the agent retrieves the physical shipping documents using `get_labels`. This removes the need for external MCP integration platforms to bridge your cloud database and your warehouse.

Run automated tracking audits.

`get_shipment_status` allows your Gemini-powered agent to audit your entire delivery pipeline. The agent pulls tracking histories for thousands of active shipments and flags delays before customers notice. For individual parcel escalations, the agent uses `get_parcel_status` to pinpoint the exact transit checkpoint. You can pipe these status updates back into Vertex AI to predict delivery anomalies.

Validate global DPD coverage.

`list_countries` lets your enterprise agent verify destination compatibility during checkout. The agent cross-references this list with your product catalog to block invalid international orders. To optimize delivery options, the agent queries `list_products` to select between standard and express shipping tiers. This ensures your Google ADK MCP workflow selects the most cost-effective service for every parcel.

Setup guide

Set up DPD MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with DPD tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="DPD_agent",
    model="gemini-2.0-flash",
    instruction="You have access to DPD tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Instantiate `McpToolset` with your Vinkius HTTP URL and pass it to your `LlmAgent`. Your Gemini model immediately gains access to all ten DPD shipping endpoints.

Yes, the agent calls `find_parcelshop` with latitude and longitude coordinates. This returns a list of active physical pickup points for customer returns or drop-offs.

The agent executes `list_shipments` with custom JSON filters to parse historical orders. You can feed this output directly into BigQuery for long-term logistics analysis.

Your agent uses `cancel_shipment` to immediately void any labels that are no longer needed. This API call stops the fulfillment process before the courier collects the physical package.

The Vinkius MCP Server runs in a zero-trust, ephemeral sandbox that isolates your customer addresses and parcel details. Your direct DPD credentials are encrypted and injected only at runtime.

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