How to Use the Handwrytten MCP in Google ADK

Q: Can Google ADK browse Handwrytten stationery?

Yes, the model calls listcards and listcategories to find matching stationery. Your Google ADK agent then uses the correct ID to mail the card.

Q: How can I limit which Handwrytten tools my agent can access?

Use the toolnames filter in Google ADK when initializing your toolset. This lets you restrict access to sensitive tools like budget checks.

Q: Where does my recipient address data go?

Recipient addresses from listaddressbook pass directly through the Vinkius secure gateway to Handwrytten. No customer address data is cached or stored in the MCP Server sandbox.

Trigger physical direct mail campaigns from Google ADK using Gemini long-context reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Handwrytten MCP to Google ADK

Create your Vinkius account to connect Handwrytten 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 Handwrytten with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scale direct mail with Google ADK

Gemini can process thousands of customer profiles from BigQuery and instantly decide who needs a physical touchpoint. This MCP Server gives your agent the ability to execute those decisions by calling `send_card` with specific handwriting styles retrieved via `list_fonts`. Google ADK handles the plumbing, exposing these physical tools to your Gemini model. The agent reads templates using `list_templates` and drafts personalized messages based on actual customer purchase history.

Track physical mail campaigns inside Google Cloud

Keep tabs on your marketing spend directly within your enterprise pipeline. Your agent can call `get_credit_balance` to monitor your account budget and query `list_orders` to log outgoing mail. If a customer asks about their delivery, Gemini can look up the specific shipment using `get_order`. This integrates your offline marketing directly with your Google Cloud database.

Address book and gift inventory management

Your enterprise agent can query `list_address_book` to find existing contacts before sending a card. It can also browse `list_gifts` to see what physical add-ons are available to pair with the stationery. The Google ADK allows you to filter which of these tools are exposed using the tool_names parameter. This prevents your agent from accidentally calling unauthorized tools or wasting budget.

Setup guide

Set up Handwrytten 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 Handwrytten 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="Handwrytten_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Handwrytten 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 Handwrytten. 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 Handwrytten 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 Handwrytten MCP in Google ADK

Instantiate McpToolset using your Vinkius MCP Server URL. Pass that toolset directly to your LlmAgent to give Gemini access to the card tools.

Yes, the model calls list_cards and list_categories to find matching stationery. Your Google ADK agent then uses the correct ID to mail the card.

Yes, Gemini can process bulk customer data and loop through the send_card tool. It uses long-context reasoning to customize each message individually.

Use the tool_names filter in Google ADK when initializing your toolset. This lets you restrict access to sensitive tools like budget checks.

Recipient addresses from list_address_book pass directly through the Vinkius secure gateway to Handwrytten. No customer address data is cached or stored in the MCP Server sandbox.

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