How to Use the Mailjet MCP in Mastra AI

Q: How do I implement human approval before Mastra AI modifies Mailjet contact lists?

You can enable the requireToolApproval flag on your Mastra agent for these MCP tools. This pauses the workflow and waits for a manual confirmation before modifying your subscriber database.

Q: What is the best way to handle invalid email errors during contact creation?

When createnewcontact encounters an invalid address, it returns an error payload. Your workflow should catch this specific exception and trigger a branch to flag the record in your database.

Trigger Mailjet workflows inside Mastra AI with automatic retries and conditional branching.

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 Mastra AI

Create your Vinkius account to connect Mailjet to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate multi-step contact onboarding

`create_new_contact` acts as the entry point for your automated onboarding pipelines in Mastra AI. When a new user registers, the agent triggers this tool and evaluates the response. If successful, the workflow moves to the next step without manual intervention. Mastra AI uses its built-in engine to execute `add_contact_to_list` right after. If the Mailjet API rate limits you, the framework handles retries with exponential backoff, ensuring no subscriber drops off the radar.

Build self-healing Mailjet email dispatch pipelines

`send_transactional_email` executes critical system notifications within your Mastra AI workflows. If an email fails to deliver, Mastra's conditional branching steps in to diagnose the issue. The workflow can instantly check `list_subscriber_lists` to verify the recipient is on an active list. This setup prevents silent failures in production. You can configure a fallback step that routes the message through an alternative channel or notifies an administrator if the API returns a hard bounce code.

Run autonomous campaign analysis

`list_marketing_campaigns` lets your Mastra AI agents audit active marketing efforts. The agent retrieves the list of campaigns, identifies the underperforming ones, and calls `get_campaign_performance` to pinpoint the drop-off points. Mastra's workflow engine can then trigger automated adjustments, like updating contact segments or flagging dead email addresses. This turns manual weekly marketing audits into a continuous, self-correcting background process.

Setup guide

Set up Mailjet MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Mailjet tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "mailjet-mcp-client",
  servers: {
    "mailjet-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Mailjet Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Mailjet tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Mailjet transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate the MCP client using the Vinkius server URL in your Mastra configuration. Call `listTools` on that client and spread the resulting array directly into your agent's tool definition array.

Yes, Mastra's workflow engine features native retry logic with exponential backoff. If `send_transactional_email` hits an API bottleneck, the framework pauses and retries the call automatically based on your policy.

You can enable the `requireToolApproval` flag on your Mastra agent for these MCP tools. This pauses the workflow and waits for a manual confirmation before modifying your subscriber database.

When `create_new_contact` encounters an invalid address, it returns an error payload. Your workflow should catch this specific exception and trigger a branch to flag the record in your database.

Your credentials remain securely stored in the Vinkius environment, never exposed to the LLM or stored in Mastra's local state. The MCP Server processes contact information in ephemeral V8 isolates, ensuring zero data persistence on the host.

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