How to Use the Iterable MCP in LangChain

Q: Can my agent edit templates using this setup?

No, this server only exposes read-only tools like listtemplates and getcampaign. Your agent can audit and analyze your assets but cannot write or modify live content, keeping your production templates safe.

Q: Where does my subscriber email data go when using this server?

When your agent calls getuser using an email address, that query runs through a secure V8 isolate sandbox. The subscriber email and campaign metrics are processed in memory and never stored on disk, keeping your customer data isolated.

Run multi-step marketing workflows using LangChain agents with direct access to your Iterable campaigns and user profiles via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Iterable MCP to LangChain

Create your Vinkius account to connect Iterable 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 Iterable with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Iterable user data directly into your prompt templates

Your LangChain agents can now pull live user profiles using `get_user` to personalize emails on the fly. Instead of hardcoding user attributes, the agent reads the profile, decides on the best angle, and drafts tailored content in a single run. You can feed this raw profile data straight into subsequent chains. For instance, the output from `list_lists` feeds directly into your segmentation prompts, letting your agent build targeted lists without manual CSV exports.

Trace Iterable MCP Server tool calls inside LangSmith

Debugging automated Iterable campaigns in LangChain gets a lot easier when you can see every single step. By exposing the Iterable MCP Server tools to your agent, you can trace exactly when `get_campaign_metrics` was called and what payload it returned. This deep observability stops silent failures in their tracks. You will see the latency and token usage for every call to `list_workflows` or `list_webhooks`, making it easy to optimize your agentic marketing pipelines.

Run multi-step campaign audits with ReAct agents

Let your LangChain ReAct agent run complete audits of your communication channels. Starting with `list_channels`, the agent checks active paths, then pulls message categories using `list_message_types` to ensure brand consistency. It doesn't stop at listing. Taking those IDs, the agent pulls specific setups via `list_templates` to flag outdated copy before it goes live to your subscribers.

Setup guide

Set up Iterable 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 Iterable 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({
    "iterable-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 Iterable 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 Iterable. 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 Iterable 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 Iterable MCP in LangChain

You should handle rate limits within your LangChain runnable configuration or agent executor loop. Since the server passes API responses directly, your chain needs backoff logic when `list_campaigns` or `get_campaign_metrics` hits API thresholds.

Yes, you can register this MCP server alongside your database tools in a single MultiServerMCPClient. This allows your LangChain agent to pull a user via `get_user` and immediately cross-reference their purchase history in your SQL database.

Your connection token is managed by Vinkius, meaning your LangChain code only needs to point to the single secure endpoint. The agent calls `list_workflows` or `list_templates` without needing to store raw API keys in your local environment.

No, this server only exposes read-only tools like `list_templates` and `get_campaign`. Your agent can audit and analyze your assets but cannot write or modify live content, keeping your production templates safe.

When your agent calls `get_user` using an email address, that query runs through a secure V8 isolate sandbox. The subscriber email and campaign metrics are processed in memory and never stored on disk, keeping your customer data isolated.

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