How to Use the AMcards MCP in LangChain

Q: How do I connect the AMcards MCP Server to my LangChain setup?

Install langchain-mcp-adapters and langgraph via pip. Initialize the MultiServerMCPClient with your Vinkius endpoint, pull the tools with client.gettools(), and pass them to your agent.

Q: Can a LangChain agent choose templates dynamically based on AMcards history?

Yes, your agent can query listcardtemplates and getcardsendinghistory in a single run. It analyzes previous mailings to select the most appropriate template for the next step.

Q: Can I run multi-server setups with AMcards and LangChain?

Yes, the MultiServerMCPClient handles multiple servers at once. You can combine this mailing toolset with your CRM database in a single agent run.

Build LangChain pipelines that mail physical greeting cards to your warmest leads based on real-time CRM events.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AMcards MCP to LangChain

Create your Vinkius account to connect AMcards 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 AMcards with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Mail physical cards directly from your LangChain agents

Stop sending boring emails when a deal closes. This MCP Server lets your LangChain agent pick a layout using `list_card_templates` and send a real, physical card via `send_greeting_card` the second a contract is signed. You feed the agent recipient details, and it handles the rest. Your agent runs the tool, and your customer gets a tangible note in their mailbox without you opening a single web browser tab.

Build multi-step AMcards drip chains in LangChain

Connect your customer touchpoints to structured physical mail sequences. Your LangChain agent can query active campaigns with `list_drip_campaigns` and immediately start a prospect on a physical mailing schedule using `trigger_drip_campaign`. Because LangChain traces everything in LangSmith, you can monitor exactly when your agent decided to trigger a physical card sequence. You get clear visibility into every tool call, ensuring you never double-send cards to the same prospect.

Track physical mail delivery inside your LangChain runs

Keep your data loops tight by monitoring what actually got delivered. Your LangChain agent runs `get_card_sending_history` to verify which contacts received cards, then uses that status to decide the next step in your sequence. You can also inspect webhook configurations via `list_configured_webhooks` to ensure your system gets instant updates when a card changes status. This turns offline physical mail into a predictable, trackable step in your software stack.

Setup guide

Set up AMcards 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 AMcards 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({
    "amcards-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 AMcards 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 AMcards. 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 AMcards 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 AMcards MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph` via pip. Initialize the `MultiServerMCPClient` with your Vinkius endpoint, pull the tools with `client.get_tools()`, and pass them to your agent.

Yes, your agent can query `list_card_templates` and `get_card_sending_history` in a single run. It analyzes previous mailings to select the most appropriate template for the next step.

The framework catches API exceptions directly during the tool call. Your agent can run `check_api_health` to verify connection status before retrying the card delivery.

Yes, the `MultiServerMCPClient` handles multiple servers at once. You can combine this mailing toolset with your CRM database in a single agent run.

Vinkius runs the server in an isolated V8 sandbox, meaning your recipient addresses and custom message text are never stored. The data passes directly through the ephemeral execution environment to the mailing API, leaving no trace behind.

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