How to Use the Handwrytten MCP in LangChain

Q: How do I connect the Handwrytten MCP Server to my LangChain agent?

Install langchain-mcp-adapters and langgraph via pip. Initialize the MultiServerMCPClient pointing to the Vinkius endpoint, retrieve the tools via client.gettools(), and pass them directly into your agent constructor.

Q: Can a LangChain agent choose fonts and templates dynamically with Handwrytten?

Yes, your agent uses listfonts and listtemplates to select the styling. It reads the available options, matches the sentiment of the message, and then feeds those IDs into sendcard.

Q: How does LangChain trace errors when a Handwrytten card fails to send?

LangSmith logs every single tool call, including inputs to sendcard and outputs from listaddressbook. If a zip code is missing or your balance is too low, the exact API error shows up in your tracing dashboard.

Build LangChain reasoning loops that trigger real ink on physical paper using this 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 LangChain

Create your Vinkius account to connect Handwrytten to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain real-world mail actions with LangChain agents

The `send_card` tool lets your LangChain agent write and mail physical Handwrytten stationery as a direct step inside your autonomous reasoning chains. Instead of just sending another ignored email, your LangChain agent evaluates customer behavior, selects a card design via `list_cards`, and sends physical Handwrytten stationery directly to their mailbox. By combining this with over 500 LangChain integrations, you can pull customer data from a database, check your remaining Handwrytten budget with `get_credit_balance`, and execute a physical mailing campaign without writing glue code. Every transition is monitored, meaning your LangChain agent can pass the output of a database lookup straight into the Handwrytten card dispatch tool.

Trace physical mail pipelines with LangSmith

The `list_orders` tool provides the exact execution history of your automated physical mail campaigns directly inside your LangChain tracing console. You can watch your LangChain agent query `get_order` to track delivery status, tracking exactly how variables like font selection from `list_fonts` or templates from `list_templates` impact processing times. This deep LangChain integration gives you full observability over token usage, latency, and tool inputs for every physical Handwrytten note sent. If a Handwrytten card fails to queue because of an address formatting error, you will see the precise payload error in LangSmith immediately.

Multi-server aggregation for smart gifting

The `list_gifts` tool works alongside other MCP servers in your LangChain setup to bundle physical items with custom Handwrytten messages. Your LangChain agent can query a local inventory database, verify item availability, and then call Handwrytten to attach gift cards or physical presents to the outgoing mail. Using the MultiServerMCPClient adapter, you configure your LangChain agent to check Handwrytten credit balances. It queries `get_credit_balance` before selecting high-value gifts, ensuring your automated LangChain customer outreach never exceeds pre-approved spend limits on Handwrytten.

Setup guide

Set up Handwrytten MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Handwrytten tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "handwrytten-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Handwrytten transactions"
    })
    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 LangChain

Install `langchain-mcp-adapters` and `langgraph` via pip. Initialize the `MultiServerMCPClient` pointing to the Vinkius endpoint, retrieve the tools via `client.get_tools()`, and pass them directly into your agent constructor.

Yes, your agent uses `list_fonts` and `list_templates` to select the styling. It reads the available options, matches the sentiment of the message, and then feeds those IDs into `send_card`.

LangSmith logs every single tool call, including inputs to `send_card` and outputs from `list_address_book`. If a zip code is missing or your balance is too low, the exact API error shows up in your tracing dashboard.

You can build chains that first check your account status with `get_credit_balance`, fetch active templates using `list_templates`, and then execute the mailing. LangChain handles the state transitions between these tool calls automatically.

Your recipient names and mailing addresses are sent directly through Vinkius's zero-trust sandbox to the Handwrytten API. No physical address data is stored or cached on the MCP server layer, keeping your customer mailing lists safe.

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