How to Use the Loops MCP in LangChain

Q: How do I run a Loops transactional email chain in LangChain?

You invoke sendtransactionalemail inside your LangChain runnable sequence. The agent receives the transaction ID and variables, triggers the email, and passes the delivery response directly to your next chain step.

Q: Can LangChain agents check Loops suppression lists?

Yes, your agent calls getcontactsuppression with the target email address before executing any email sends. If the API returns a suppressed status, LangChain halts the active chain execution.

Q: How does LangChain handle Loops API errors during contact creation?

When createcontact fails, LangChain captures the API error directly in your LangSmith traces. You can design your agent to catch this error and automatically try running updatecontact instead.

Run multi-step email workflows in LangChain by chaining Loops contacts, events, and transactional triggers directly using this 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 Loops MCP to LangChain

Create your Vinkius account to connect Loops 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 Loops with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Loops actions in LangChain

`send_event` kicks off automated user journeys by passing output from previous steps in your LangChain chain directly to Loops. Your agent runs the tool, checks the execution in LangSmith, and routes the next action based on real-time Loops event status. Here's the thing: you pass contact metadata from LangChain database queries straight into `create_contact` in Loops without writing custom glue code. LangChain handles the data flow, letting the agent evaluate the Loops result before deciding to trigger the next email.

Verify Loops subscriber status using LangChain MCP Server tools

`get_contact_suppression` stops your LangChain agent from sending emails to opted-out Loops addresses by checking their status before running transactional runs. The agent queries this Loops suppression tool inside its LangChain decision loop to protect your domain reputation. Look, if the address is clean, the LangChain agent proceeds to invoke `send_transactional_email` in Loops using the exact template variables required. LangSmith traces every Loops parameter, giving you clear visibility into what your agent sent and why.

Update Loops audience lists through LangChain agents

`update_contact` modifies existing contact properties in Loops based on user behavior tracked during LangChain chain runs. Your LangChain agent calls this tool to sync Loops user groups or update first names when a user changes their profile details. The LangChain agent first runs `find_contact` to locate the correct Loops profile ID, then chains that output directly into the update payload. This keeps your Loops marketing lists accurate inside your LangChain pipelines without manual exports or cron jobs when integrated with your MCP client.

Setup guide

Set up Loops 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 Loops 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({
    "loops-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 Loops 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 Loops. 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 Loops 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 Loops MCP in LangChain

You invoke `send_transactional_email` inside your LangChain runnable sequence. The agent receives the transaction ID and variables, triggers the email, and passes the delivery response directly to your next chain step.

Yes, your agent calls `get_contact_suppression` with the target email address before executing any email sends. If the API returns a suppressed status, LangChain halts the active chain execution.

When `create_contact` fails, LangChain captures the API error directly in your LangSmith traces. You can design your agent to catch this error and automatically try running `update_contact` instead.

You use LangSmith to trace the exact JSON payload passed to `send_event` or `send_transactional_email`. Every tool call records the input parameters and API response in your trace timeline.

The server processes emails, names, and user group data inside an ephemeral V8 sandbox. Your credentials never touch disk, and the endpoint token keeps your Loops API key isolated from the LangChain runtime environment.

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