How to Use the Cordial MCP in LangChain

Q: Can my LangChain chain update Cordial subscriber attributes?

Yes, your agent uses upsertsubscriber to modify attributes in the middle of a chain run. The output of previous steps feeds directly into this tool to keep profiles fresh.

Q: Can I search for campaigns by name?

You can use searchcampaignsbyname to find specific marketing campaigns. The tool returns matching campaign profiles and scheduling data for your agent to process.

Run multi-step marketing workflows where your LangChain agent reads Cordial data and updates subscriber profiles dynamically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cordial MCP to LangChain

Create your Vinkius account to connect Cordial 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 Cordial with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync subscriber profiles inside LangChain chains

`upsert_subscriber` writes profile updates directly to Cordial whenever your chain processes a customer interaction. This tool handles identity properties, custom attributes, and channel preferences without manual API calls. Your LangChain agent pairs this with `get_subscriber_profile` to pull device tokens and list memberships before executing the next link in your workflow. Having these tools inside your chain means you can branch your logic based on real-time subscriber states.

Audit automated messaging with LangSmith tracing

`list_automation_messages` exposes active workflows and triggered communications directly to your LangChain setup. You can view the exact JSON payload sent to Cordial right inside your LangSmith dashboard to trace latency and token usage. Use `list_messages` to check transactional templates and subject lines when debugging a failing chain link. This visibility helps you catch formatting errors before they reach your customers.

Query audience segments using this MCP Server

`list_audience_segments` pulls segment IDs and subscriber counts so your agent can target the right list. This MCP tool provides the raw metrics needed to decide which campaign to trigger next. You can feed these segment properties into `list_marketing_campaigns` to analyze performance trends across specific groups. This setup lets your LangChain runner make automated decisions based on current group sizes.

Setup guide

Set up Cordial 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 Cordial 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({
    "cordial-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 Cordial 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 Cordial. 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 Cordial 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 Cordial MCP in LangChain

Install the adapter package and initialize the client with your Vinkius MCP endpoint. Pass the tools from `client.get_tools()` directly into your agent constructor to let it call Cordial endpoints.

Yes, your agent uses `upsert_subscriber` to modify attributes in the middle of a chain run. The output of previous steps feeds directly into this tool to keep profiles fresh.

The runtime catches API failures and passes the raw error message back to your agent. You can configure retry logic or fallback chains in LangGraph to handle these MCP exceptions gracefully.

You can use `search_campaigns_by_name` to find specific marketing campaigns. The tool returns matching campaign profiles and scheduling data for your agent to process.

Your subscriber emails and device tokens pass through Vinkius inside an isolated V8 sandbox. We never store this contact data, and all execution environments are destroyed immediately after your tool call finishes.

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