How to Use the Cardly MCP in LangChain

Q: How do I initialize Cardly tools in LangChain?

Install langchain-mcp-adapters. Pass the Cardly endpoint to MultiServerMCPClient and call gettools() to feed your agent.

Build multi-step physical mail pipelines using Cardly tools directly inside your LangChain ReAct agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cardly MCP to LangChain

Create your Vinkius account to connect Cardly 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 Cardly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LangChain ReAct agents for physical mail

Your agent calls `list_card_artwork` to pull available designs before deciding which physical card fits the user's prompt. LangChain passes that output directly into `preview_greeting_card` to generate a mockup. You track every token spent during this decision loop using LangSmith. The agent evaluates the preview, confirms the design matches the intent, and finally triggers `place_greeting_card_order` to dispatch real mail.

Chain contact lookups with orders

Calling `find_contact` checks your existing lists for an email address before processing a new shipment. If the lookup fails, your graph branches to execute `add_contact_to_list` and creates the record automatically. This prevents duplicate entries in your address book. Developers build these conditional paths into their chains to handle missing data without crashing the pipeline.

Observe Cardly MCP Server latency

Running `verify_api_connection` confirms your authentication status at the start of a run. LangSmith records the exact milliseconds this check takes, along with the payload size of the response. Tracing gives you hard numbers on API performance. When `get_account_info` runs to check your balance, you see exactly what the LLM saw when deciding if there were enough funds to mail a card.

Setup guide

Set up Cardly 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 Cardly 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({
    "cardly-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 Cardly 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 Cardly. 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 Cardly 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 Cardly MCP in LangChain

Install `langchain-mcp-adapters`. Pass the Cardly endpoint to `MultiServerMCPClient` and call `get_tools()` to feed your agent.

Yes. Your agent reads an address from Postgres, then passes those variables into the Cardly `place_greeting_card_order` tool.

It logs every tool input and output. You see exactly how many tokens the agent spent parsing the `list_contact_lists` response.

You might be passing raw strings instead of structured arguments. Check your LangSmith traces to see what the agent actually sent to `get_artwork_details`.

Vinkius runs the Cardly integration inside a V8 Isolate Sandbox. Physical mailing addresses and email contacts stay in memory only while the tool executes, then the sandbox is destroyed immediately.

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