How to Use the Handwrytten MCP in AutoGen

Q: How do I register the Handwrytten MCP Server with AutoGen?

Install autogen-extmcp and use the mcpservertools helper with your Vinkius MCP server URL. Pass the resulting tool list to your AssistantAgent constructor to give them physical mailing capabilities.

Q: How do AutoGen agents collaborate to send a Handwrytten card?

One agent drafts the message using listtemplates, another selects the font with listfonts, and a third verifies the budget via getcreditbalance before the execution agent calls sendcard.

Q: Can AutoGen agents handle physical gift selection with Handwrytten?

Yes, your agents can query listgifts to see available add-ons. They can debate which gift fits the customer's profile and budget, then include the gift ID in the final mailing order.

Q: How do AutoGen agents track delivery issues with Handwrytten?

A dedicated tracking agent can periodically call listorders and check specific shipments with getorder. If a delivery fails, the agent triggers a discussion to decide on a correction.

Let AutoGen agents debate card designs and run consensus-driven physical mail campaigns via the Handwrytten MCP Server.

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 AutoGen

Create your Vinkius account to connect Handwrytten to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven physical card selection

The `list_cards` tool allows your AutoGen agents to debate which physical Handwrytten stationery is appropriate for a high-value client. An AutoGen marketing agent can propose a card category using `list_categories`, while a finance agent checks the Handwrytten budget with `get_credit_balance` to approve the cost. This multi-agent AutoGen conversation prevents costly mistakes in physical Handwrytten mail automation. The AutoGen agents negotiate the best approach, choosing the ideal font from `list_fonts` and verifying that the stationery matches the Handwrytten campaign goals before any paper is printed.

Multi-agent validation for Handwrytten MCP Server campaigns

The `send_card` tool is only executed after your AutoGen safety agent validates the recipient details against your Handwrytten address records. The AutoGen safety agent queries `list_address_book` to confirm the address is complete, while a copywriter agent refines the message text to fit the Handwrytten template constraints from `list_templates`. This collaborative AutoGen pipeline ensures zero wasted spend on returned physical Handwrytten mail. By separating the validation, copywriting, and execution roles inside AutoGen, your agents catch formatting errors and spelling mistakes before triggering the actual Handwrytten printing press.

Automated order tracking and escalation

The `list_orders` tool lets an AutoGen tracking agent monitor the progress of physical Handwrytten mailings. If an order status retrieved via `get_order` indicates a delivery failure, the AutoGen tracking agent initiates a debate with the customer support agent to resolve the issue. This AutoGen loop operates entirely in the background to manage physical Handwrytten shipments. The AutoGen agents can automatically decide to send a replacement card or alert a human team member, using the historical data to optimize future font and gift choices from `list_gifts`.

Setup guide

Set up Handwrytten MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Handwrytten tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Handwrytten_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Handwrytten data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Handwrytten_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Handwrytten data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]` and use the `mcp_server_tools` helper with your Vinkius MCP server URL. Pass the resulting tool list to your `AssistantAgent` constructor to give them physical mailing capabilities.

One agent drafts the message using `list_templates`, another selects the font with `list_fonts`, and a third verifies the budget via `get_credit_balance` before the execution agent calls `send_card`.

Yes, your agents can query `list_gifts` to see available add-ons. They can debate which gift fits the customer's profile and budget, then include the gift ID in the final mailing order.

A dedicated tracking agent can periodically call `list_orders` and check specific shipments with `get_order`. If a delivery fails, the agent triggers a discussion to decide on a correction.

The text of your physical cards is transmitted directly to Handwrytten's secure print queue through Vinkius's ephemeral, zero-trust sandbox. No message content is written to disk or used to train models during the multi-agent execution.

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