How to Use the Mailjet MCP in LangChain

Q: How do I connect the Mailjet MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph. Initialize a MultiServerMCPClient with your HTTP transport URL, then pass the tools from client.gettools() into your agent constructor.

Q: Can my LangChain agent send plain text emails via Mailjet?

Yes. The agent can construct a message and call sendplainemail directly. It works well for simple alerts where you skip HTML formatting entirely.

Q: How does LangChain handle Mailjet API rate limits?

Your agent executes tools sequentially. If getcampaignperformance hits a limit, you can configure LangChain's retry parsers to back off and try again.

Q: What Mailjet template tools work with LangChain?

Your agent has access to listemailtemplates and gettemplatedetails. It can read the available templates before deciding which one to use for a specific user interaction.

Build complex email automation pipelines by linking Mailjet to your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mailjet MCP to LangChain

Create your Vinkius account to connect Mailjet 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 Mailjet with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Campaign Execution in LangChain

LangChain agents excel at multi-step reasoning. You can wire up a chain that pulls user data from your database, formats it, and fires off notifications using `send_template_email`. The agent decides which template ID to grab by calling `list_email_templates` first. You get full observability in LangSmith. Every time your MCP Server hits `subscribe_to_list` or `create_new_contact`, you see the exact token usage and latency. It turns raw email operations into measurable steps within your broader application logic.

Automated Analytics Reporting with MCP

Stop writing custom scripts to pull weekly email stats. Your ReAct agent can autonomously call `get_account_analytics` and `list_sent_campaigns` to gather the raw metrics. It parses the JSON output and passes it down the chain. The next link in your chain can format those numbers into a Slack message or a PDF report. If a specific campaign looks off, the agent dives deeper with `get_campaign_performance` to pinpoint the drop in open rates before alerting your team.

Dynamic Audience Management

Managing contact lists manually is a waste of time. You can build a LangChain pipeline that listens to webhooks and automatically sorts users. The agent uses `list_contact_groups` to find the right segment, then executes `create_new_contact`. If a user upgrades their subscription, your chain handles the transition. It pulls their current status via `list_all_contacts` and pushes them into the premium tier with `subscribe_to_list`. The logic stays entirely within your agent's decision tree.

Setup guide

Set up Mailjet 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 Mailjet 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({
    "mailjet-alternative-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 Mailjet 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 Mailjet. 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 Mailjet 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 Mailjet MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph`. Initialize a `MultiServerMCPClient` with your HTTP transport URL, then pass the tools from `client.get_tools()` into your agent constructor.

Yes. The agent can construct a message and call `send_plain_email` directly. It works well for simple alerts where you skip HTML formatting entirely.

Your agent executes tools sequentially. If `get_campaign_performance` hits a limit, you can configure LangChain's retry parsers to back off and try again.

Your agent has access to `list_email_templates` and `get_template_details`. It can read the available templates before deciding which one to use for a specific user interaction.

The server processes email addresses and campaign metrics strictly in memory. LangChain passes the tool arguments to the isolated V8 sandbox, and the data disappears the moment the execution 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